Artificial intelligence

Subterms

    More stories

    • 100 Shares99 Views

      in Data Management & Statistics

      Building explainability into the components of machine-learning models

      by

      Explanation methods that help users understand and trust machine-learning models often describe how much certain features used in the model contribute to its prediction. For example, if a model predicts a patient’s risk of developing cardiac disease, a physician might want to know how strongly the patient’s heart rate data influences that prediction.

      But if those features are so complex or convoluted that the user can’t understand them, does the explanation method do any good?

      MIT researchers are striving to improve the interpretability of features so decision makers will be more comfortable using the outputs of machine-learning models. Drawing on years of field work, they developed a taxonomy to help developers craft features that will be easier for their target audience to understand.

      “We found that out in the real world, even though we were using state-of-the-art ways of explaining machine-learning models, there is still a lot of confusion stemming from the features, not from the model itself,” says Alexandra Zytek, an electrical engineering and computer science PhD student and lead author of a paper introducing the taxonomy.

      To build the taxonomy, the researchers defined properties that make features interpretable for five types of users, from artificial intelligence experts to the people affected by a machine-learning model’s prediction. They also offer instructions for how model creators can transform features into formats that will be easier for a layperson to comprehend.

      They hope their work will inspire model builders to consider using interpretable features from the beginning of the development process, rather than trying to work backward and focus on explainability after the fact.

      MIT co-authors include Dongyu Liu, a postdoc; visiting professor Laure Berti-Équille, research director at IRD; and senior author Kalyan Veeramachaneni, principal research scientist in the Laboratory for Information and Decision Systems (LIDS) and leader of the Data to AI group. They are joined by Ignacio Arnaldo, a principal data scientist at Corelight. The research is published in the June edition of the Association for Computing Machinery Special Interest Group on Knowledge Discovery and Data Mining’s peer-reviewed Explorations Newsletter.

      Real-world lessons

      Features are input variables that are fed to machine-learning models; they are usually drawn from the columns in a dataset. Data scientists typically select and handcraft features for the model, and they mainly focus on ensuring features are developed to improve model accuracy, not on whether a decision-maker can understand them, Veeramachaneni explains.

      For several years, he and his team have worked with decision makers to identify machine-learning usability challenges. These domain experts, most of whom lack machine-learning knowledge, often don’t trust models because they don’t understand the features that influence predictions.

      For one project, they partnered with clinicians in a hospital ICU who used machine learning to predict the risk a patient will face complications after cardiac surgery. Some features were presented as aggregated values, like the trend of a patient’s heart rate over time. While features coded this way were “model ready” (the model could process the data), clinicians didn’t understand how they were computed. They would rather see how these aggregated features relate to original values, so they could identify anomalies in a patient’s heart rate, Liu says.

      By contrast, a group of learning scientists preferred features that were aggregated. Instead of having a feature like “number of posts a student made on discussion forums” they would rather have related features grouped together and labeled with terms they understood, like “participation.”

      “With interpretability, one size doesn’t fit all. When you go from area to area, there are different needs. And interpretability itself has many levels,” Veeramachaneni says.

      The idea that one size doesn’t fit all is key to the researchers’ taxonomy. They define properties that can make features more or less interpretable for different decision makers and outline which properties are likely most important to specific users.

      For instance, machine-learning developers might focus on having features that are compatible with the model and predictive, meaning they are expected to improve the model’s performance.

      On the other hand, decision makers with no machine-learning experience might be better served by features that are human-worded, meaning they are described in a way that is natural for users, and understandable, meaning they refer to real-world metrics users can reason about.

      “The taxonomy says, if you are making interpretable features, to what level are they interpretable? You may not need all levels, depending on the type of domain experts you are working with,” Zytek says.

      Putting interpretability first

      The researchers also outline feature engineering techniques a developer can employ to make features more interpretable for a specific audience.

      Feature engineering is a process in which data scientists transform data into a format machine-learning models can process, using techniques like aggregating data or normalizing values. Most models also can’t process categorical data unless they are converted to a numerical code. These transformations are often nearly impossible for laypeople to unpack.

      Creating interpretable features might involve undoing some of that encoding, Zytek says. For instance, a common feature engineering technique organizes spans of data so they all contain the same number of years. To make these features more interpretable, one could group age ranges using human terms, like infant, toddler, child, and teen. Or rather than using a transformed feature like average pulse rate, an interpretable feature might simply be the actual pulse rate data, Liu adds.

      “In a lot of domains, the tradeoff between interpretable features and model accuracy is actually very small. When we were working with child welfare screeners, for example, we retrained the model using only features that met our definitions for interpretability, and the performance decrease was almost negligible,” Zytek says.

      Building off this work, the researchers are developing a system that enables a model developer to handle complicated feature transformations in a more efficient manner, to create human-centered explanations for machine-learning models. This new system will also convert algorithms designed to explain model-ready datasets into formats that can be understood by decision makers. More

    • 88 Shares99 Views

      in Data Management & Statistics

      Exploring emerging topics in artificial intelligence policy

      by

      Members of the public sector, private sector, and academia convened for the second AI Policy Forum Symposium last month to explore critical directions and questions posed by artificial intelligence in our economies and societies.

      The virtual event, hosted by the AI Policy Forum (AIPF) — an undertaking by the MIT Schwarzman College of Computing to bridge high-level principles of AI policy with the practices and trade-offs of governing — brought together an array of distinguished panelists to delve into four cross-cutting topics: law, auditing, health care, and mobility.

      In the last year there have been substantial changes in the regulatory and policy landscape around AI in several countries — most notably in Europe with the development of the European Union Artificial Intelligence Act, the first attempt by a major regulator to propose a law on artificial intelligence. In the United States, the National AI Initiative Act of 2020, which became law in January 2021, is providing a coordinated program across federal government to accelerate AI research and application for economic prosperity and security gains. Finally, China recently advanced several new regulations of its own.

      Each of these developments represents a different approach to legislating AI, but what makes a good AI law? And when should AI legislation be based on binding rules with penalties versus establishing voluntary guidelines?

      Jonathan Zittrain, professor of international law at Harvard Law School and director of the Berkman Klein Center for Internet and Society, says the self-regulatory approach taken during the expansion of the internet had its limitations with companies struggling to balance their interests with those of their industry and the public.

      “One lesson might be that actually having representative government take an active role early on is a good idea,” he says. “It’s just that they’re challenged by the fact that there appears to be two phases in this environment of regulation. One, too early to tell, and two, too late to do anything about it. In AI I think a lot of people would say we’re still in the ‘too early to tell’ stage but given that there’s no middle zone before it’s too late, it might still call for some regulation.”

      A theme that came up repeatedly throughout the first panel on AI laws — a conversation moderated by Dan Huttenlocher, dean of the MIT Schwarzman College of Computing and chair of the AI Policy Forum — was the notion of trust. “If you told me the truth consistently, I would say you are an honest person. If AI could provide something similar, something that I can say is consistent and is the same, then I would say it’s trusted AI,” says Bitange Ndemo, professor of entrepreneurship at the University of Nairobi and the former permanent secretary of Kenya’s Ministry of Information and Communication.

      Eva Kaili, vice president of the European Parliament, adds that “In Europe, whenever you use something, like any medication, you know that it has been checked. You know you can trust it. You know the controls are there. We have to achieve the same with AI.” Kalli further stresses that building trust in AI systems will not only lead to people using more applications in a safe manner, but that AI itself will reap benefits as greater amounts of data will be generated as a result.

      The rapidly increasing applicability of AI across fields has prompted the need to address both the opportunities and challenges of emerging technologies and the impact they have on social and ethical issues such as privacy, fairness, bias, transparency, and accountability. In health care, for example, new techniques in machine learning have shown enormous promise for improving quality and efficiency, but questions of equity, data access and privacy, safety and reliability, and immunology and global health surveillance remain at large.

      MIT’s Marzyeh Ghassemi, an assistant professor in the Department of Electrical Engineering and Computer Science and the Institute for Medical Engineering and Science, and David Sontag, an associate professor of electrical engineering and computer science, collaborated with Ziad Obermeyer, an associate professor of health policy and management at the University of California Berkeley School of Public Health, to organize AIPF Health Wide Reach, a series of sessions to discuss issues of data sharing and privacy in clinical AI. The organizers assembled experts devoted to AI, policy, and health from around the world with the goal of understanding what can be done to decrease barriers to access to high-quality health data to advance more innovative, robust, and inclusive research results while being respectful of patient privacy.

      Over the course of the series, members of the group presented on a topic of expertise and were tasked with proposing concrete policy approaches to the challenge discussed. Drawing on these wide-ranging conversations, participants unveiled their findings during the symposium, covering nonprofit and government success stories and limited access models; upside demonstrations; legal frameworks, regulation, and funding; technical approaches to privacy; and infrastructure and data sharing. The group then discussed some of their recommendations that are summarized in a report that will be released soon.

      One of the findings calls for the need to make more data available for research use. Recommendations that stem from this finding include updating regulations to promote data sharing to enable easier access to safe harbors such as the Health Insurance Portability and Accountability Act (HIPAA) has for de-identification, as well as expanding funding for private health institutions to curate datasets, amongst others. Another finding, to remove barriers to data for researchers, supports a recommendation to decrease obstacles to research and development on federally created health data. “If this is data that should be accessible because it’s funded by some federal entity, we should easily establish the steps that are going to be part of gaining access to that so that it’s a more inclusive and equitable set of research opportunities for all,” says Ghassemi. The group also recommends taking a careful look at the ethical principles that govern data sharing. While there are already many principles proposed around this, Ghassemi says that “obviously you can’t satisfy all levers or buttons at once, but we think that this is a trade-off that’s very important to think through intelligently.”

      In addition to law and health care, other facets of AI policy explored during the event included auditing and monitoring AI systems at scale, and the role AI plays in mobility and the range of technical, business, and policy challenges for autonomous vehicles in particular.

      The AI Policy Forum Symposium was an effort to bring together communities of practice with the shared aim of designing the next chapter of AI. In his closing remarks, Aleksander Madry, the Cadence Designs Systems Professor of Computing at MIT and faculty co-lead of the AI Policy Forum, emphasized the importance of collaboration and the need for different communities to communicate with each other in order to truly make an impact in the AI policy space.

      “The dream here is that we all can meet together — researchers, industry, policymakers, and other stakeholders — and really talk to each other, understand each other’s concerns, and think together about solutions,” Madry said. “This is the mission of the AI Policy Forum and this is what we want to enable.” More

    • 63 Shares149 Views

      in Data Management & Statistics

      Robots play with play dough

      by

      The inner child in many of us feels an overwhelming sense of joy when stumbling across a pile of the fluorescent, rubbery mixture of water, salt, and flour that put goo on the map: play dough. (Even if this happens rarely in adulthood.)

      While manipulating play dough is fun and easy for 2-year-olds, the shapeless sludge is hard for robots to handle. Machines have become increasingly reliable with rigid objects, but manipulating soft, deformable objects comes with a laundry list of technical challenges, and most importantly, as with most flexible structures, if you move one part, you’re likely affecting everything else. 

      Scientists from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) and Stanford University recently let robots take their hand at playing with the modeling compound, but not for nostalgia’s sake. Their new system learns directly from visual inputs to let a robot with a two-fingered gripper see, simulate, and shape doughy objects. “RoboCraft” could reliably plan a robot’s behavior to pinch and release play dough to make various letters, including ones it had never seen. With just 10 minutes of data, the two-finger gripper rivaled human counterparts that teleoperated the machine — performing on-par, and at times even better, on the tested tasks. 

      “Modeling and manipulating objects with high degrees of freedom are essential capabilities for robots to learn how to enable complex industrial and household interaction tasks, like stuffing dumplings, rolling sushi, and making pottery,” says Yunzhu Li, CSAIL PhD student and author on a new paper about RoboCraft. “While there’s been recent advances in manipulating clothes and ropes, we found that objects with high plasticity, like dough or plasticine — despite ubiquity in those household and industrial settings — was a largely underexplored territory. With RoboCraft, we learn the dynamics models directly from high-dimensional sensory data, which offers a promising data-driven avenue for us to perform effective planning.” 

      Play video

      With undefined, smooth material, the whole structure needs to be accounted for before you can do any type of efficient and effective modeling and planning. By turning the images into graphs of little particles, coupled with algorithms, RoboCraft, using a graph neural network as the dynamics model, makes more accurate predictions about the material’s change of shapes. 

      Typically, researchers have used complex physics simulators to model and understand force and dynamics being applied to objects, but RoboCraft simply uses visual data. The inner-workings of the system relies on three parts to shape soft material into, say, an “R.” 

      The first part — perception — is all about learning to “see.” It uses cameras to collect raw, visual sensor data from the environment, which are then turned into little clouds of particles to represent the shapes. A graph-based neural network then uses said particle data to learn to “simulate” the object’s dynamics, or how it moves. Then, algorithms help plan the robot’s behavior so it learns to “shape” a blob of dough, armed with the training data from the many pinches. While the letters are a bit loose, they’re indubitably representative. 

      Besides cutesy shapes, the team is (actually) working on making dumplings from dough and a prepared filling. Right now, with just a two finger gripper, it’s a big ask. RoboCraft would need additional tools (a baker needs multiple tools to cook; so do robots) — a rolling pin, a stamp, and a mold. 

      A more far in the future domain the scientists envision is using RoboCraft for assistance with household tasks and chores, which could be of particular help to the elderly or those with limited mobility. To accomplish this, given the many obstructions that could take place, a much more adaptive representation of the dough or item would be needed, and as well as exploration into what class of models might be suitable to capture the underlying structural systems. 

      “RoboCraft essentially demonstrates that this predictive model can be learned in very data-efficient ways to plan motion. In the long run, we are thinking about using various tools to manipulate materials,” says Li. “If you think about dumpling or dough making, just one gripper wouldn’t be able to solve it. Helping the model understand and accomplish longer-horizon planning tasks, such as, how the dough will deform given the current tool, movements and actions, is a next step for future work.” 

      Li wrote the paper alongside Haochen Shi, Stanford master’s student; Huazhe Xu, Stanford postdoc; Zhiao Huang, PhD student at the University of California at San Diego; and Jiajun Wu, assistant professor at Stanford. They will present the research at the Robotics: Science and Systems conference in New York City. The work is in part supported by the Stanford Institute for Human-Centered AI (HAI), the Samsung Global Research Outreach (GRO) Program, the Toyota Research Institute (TRI), and Amazon, Autodesk, Salesforce, and Bosch. More

    • 100 Shares109 Views

      in Data Management & Statistics

      Researchers release open-source photorealistic simulator for autonomous driving

      by

      Hyper-realistic virtual worlds have been heralded as the best driving schools for autonomous vehicles (AVs), since they’ve proven fruitful test beds for safely trying out dangerous driving scenarios. Tesla, Waymo, and other self-driving companies all rely heavily on data to enable expensive and proprietary photorealistic simulators, since testing and gathering nuanced I-almost-crashed data usually isn’t the most easy or desirable to recreate. 

      To that end, scientists from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) created “VISTA 2.0,” a data-driven simulation engine where vehicles can learn to drive in the real world and recover from near-crash scenarios. What’s more, all of the code is being open-sourced to the public. 

      “Today, only companies have software like the type of simulation environments and capabilities of VISTA 2.0, and this software is proprietary. With this release, the research community will have access to a powerful new tool for accelerating the research and development of adaptive robust control for autonomous driving,” says MIT Professor and CSAIL Director Daniela Rus, senior author on a paper about the research. 

      Play video

      VISTA is a data-driven, photorealistic simulator for autonomous driving. It can simulate not just live video but LiDAR data and event cameras, and also incorporate other simulated vehicles to model complex driving situations. VISTA is open source and the code can be found below.

      VISTA 2.0 builds off of the team’s previous model, VISTA, and it’s fundamentally different from existing AV simulators since it’s data-driven — meaning it was built and photorealistically rendered from real-world data — thereby enabling direct transfer to reality. While the initial iteration supported only single car lane-following with one camera sensor, achieving high-fidelity data-driven simulation required rethinking the foundations of how different sensors and behavioral interactions can be synthesized. 

      Enter VISTA 2.0: a data-driven system that can simulate complex sensor types and massively interactive scenarios and intersections at scale. With much less data than previous models, the team was able to train autonomous vehicles that could be substantially more robust than those trained on large amounts of real-world data. 

      “This is a massive jump in capabilities of data-driven simulation for autonomous vehicles, as well as the increase of scale and ability to handle greater driving complexity,” says Alexander Amini, CSAIL PhD student and co-lead author on two new papers, together with fellow PhD student Tsun-Hsuan Wang. “VISTA 2.0 demonstrates the ability to simulate sensor data far beyond 2D RGB cameras, but also extremely high dimensional 3D lidars with millions of points, irregularly timed event-based cameras, and even interactive and dynamic scenarios with other vehicles as well.” 

      The team was able to scale the complexity of the interactive driving tasks for things like overtaking, following, and negotiating, including multiagent scenarios in highly photorealistic environments. 

      Training AI models for autonomous vehicles involves hard-to-secure fodder of different varieties of edge cases and strange, dangerous scenarios, because most of our data (thankfully) is just run-of-the-mill, day-to-day driving. Logically, we can’t just crash into other cars just to teach a neural network how to not crash into other cars.

      Recently, there’s been a shift away from more classic, human-designed simulation environments to those built up from real-world data. The latter have immense photorealism, but the former can easily model virtual cameras and lidars. With this paradigm shift, a key question has emerged: Can the richness and complexity of all of the sensors that autonomous vehicles need, such as lidar and event-based cameras that are more sparse, accurately be synthesized? 

      Lidar sensor data is much harder to interpret in a data-driven world — you’re effectively trying to generate brand-new 3D point clouds with millions of points, only from sparse views of the world. To synthesize 3D lidar point clouds, the team used the data that the car collected, projected it into a 3D space coming from the lidar data, and then let a new virtual vehicle drive around locally from where that original vehicle was. Finally, they projected all of that sensory information back into the frame of view of this new virtual vehicle, with the help of neural networks. 

      Together with the simulation of event-based cameras, which operate at speeds greater than thousands of events per second, the simulator was capable of not only simulating this multimodal information, but also doing so all in real time — making it possible to train neural nets offline, but also test online on the car in augmented reality setups for safe evaluations. “The question of if multisensor simulation at this scale of complexity and photorealism was possible in the realm of data-driven simulation was very much an open question,” says Amini. 

      With that, the driving school becomes a party. In the simulation, you can move around, have different types of controllers, simulate different types of events, create interactive scenarios, and just drop in brand new vehicles that weren’t even in the original data. They tested for lane following, lane turning, car following, and more dicey scenarios like static and dynamic overtaking (seeing obstacles and moving around so you don’t collide). With the multi-agency, both real and simulated agents interact, and new agents can be dropped into the scene and controlled any which way. 

      Taking their full-scale car out into the “wild” — a.k.a. Devens, Massachusetts — the team saw  immediate transferability of results, with both failures and successes. They were also able to demonstrate the bodacious, magic word of self-driving car models: “robust.” They showed that AVs, trained entirely in VISTA 2.0, were so robust in the real world that they could handle that elusive tail of challenging failures. 

      Now, one guardrail humans rely on that can’t yet be simulated is human emotion. It’s the friendly wave, nod, or blinker switch of acknowledgement, which are the type of nuances the team wants to implement in future work. 

      “The central algorithm of this research is how we can take a dataset and build a completely synthetic world for learning and autonomy,” says Amini. “It’s a platform that I believe one day could extend in many different axes across robotics. Not just autonomous driving, but many areas that rely on vision and complex behaviors. We’re excited to release VISTA 2.0 to help enable the community to collect their own datasets and convert them into virtual worlds where they can directly simulate their own virtual autonomous vehicles, drive around these virtual terrains, train autonomous vehicles in these worlds, and then can directly transfer them to full-sized, real self-driving cars.” 

      Amini and Wang wrote the paper alongside Zhijian Liu, MIT CSAIL PhD student; Igor Gilitschenski, assistant professor in computer science at the University of Toronto; Wilko Schwarting, AI research scientist and MIT CSAIL PhD ’20; Song Han, associate professor at MIT’s Department of Electrical Engineering and Computer Science; Sertac Karaman, associate professor of aeronautics and astronautics at MIT; and Daniela Rus, MIT professor and CSAIL director. The researchers presented the work at the IEEE International Conference on Robotics and Automation (ICRA) in Philadelphia. 

      This work was supported by the National Science Foundation and Toyota Research Institute. The team acknowledges the support of NVIDIA with the donation of the Drive AGX Pegasus. More

    • 63 Shares189 Views

      in Data Management & Statistics

      Hallucinating to better text translation

      by

      As babies, we babble and imitate our way to learning languages. We don’t start off reading raw text, which requires fundamental knowledge and understanding about the world, as well as the advanced ability to interpret and infer descriptions and relationships. Rather, humans begin our language journey slowly, by pointing and interacting with our environment, basing our words and perceiving their meaning through the context of the physical and social world. Eventually, we can craft full sentences to communicate complex ideas.

      Similarly, when humans begin learning and translating into another language, the incorporation of other sensory information, like multimedia, paired with the new and unfamiliar words, like flashcards with images, improves language acquisition and retention. Then, with enough practice, humans can accurately translate new, unseen sentences in context without the accompanying media; however, imagining a picture based on the original text helps.

      This is the basis of a new machine learning model, called VALHALLA, by researchers from MIT, IBM, and the University of California at San Diego, in which a trained neural network sees a source sentence in one language, hallucinates an image of what it looks like, and then uses both to translate into a target language. The team found that their method demonstrates improved accuracy of machine translation over text-only translation. Further, it provided an additional boost for cases with long sentences, under-resourced languages, and instances where part of the source sentence is inaccessible to the machine translator.

      As a core task within the AI field of natural language processing (NLP), machine translation is an “eminently practical technology that’s being used by millions of people every day,” says study co-author Yoon Kim, assistant professor in MIT’s Department of Electrical Engineering and Computer Science with affiliations in the Computer Science and Artificial Intelligence Laboratory (CSAIL) and the MIT-IBM Watson AI Lab. With recent, significant advances in deep learning, “there’s been an interesting development in how one might use non-text information — for example, images, audio, or other grounding information — to tackle practical tasks involving language” says Kim, because “when humans are performing language processing tasks, we’re doing so within a grounded, situated world.” The pairing of hallucinated images and text during inference, the team postulated, imitates that process, providing context for improved performance over current state-of-the-art techniques, which utilize text-only data.

      This research will be presented at the IEEE / CVF Computer Vision and Pattern Recognition Conference this month. Kim’s co-authors are UC San Diego graduate student Yi Li and Professor Nuno Vasconcelos, along with research staff members Rameswar Panda, Chun-fu “Richard” Chen, Rogerio Feris, and IBM Director David Cox of IBM Research and the MIT-IBM Watson AI Lab.

      Learning to hallucinate from images

      When we learn new languages and to translate, we’re often provided with examples and practice before venturing out on our own. The same is true for machine-translation systems; however, if images are used during training, these AI methods also require visual aids for testing, limiting their applicability, says Panda.

      “In real-world scenarios, you might not have an image with respect to the source sentence. So, our motivation was basically: Instead of using an external image during inference as input, can we use visual hallucination — the ability to imagine visual scenes — to improve machine translation systems?” says Panda.

      To do this, the team used an encoder-decoder architecture with two transformers, a type of neural network model that’s suited for sequence-dependent data, like language, that can pay attention key words and semantics of a sentence. One transformer generates a visual hallucination, and the other performs multimodal translation using outputs from the first transformer.

      During training, there are two streams of translation: a source sentence and a ground-truth image that is paired with it, and the same source sentence that is visually hallucinated to make a text-image pair. First the ground-truth image and sentence are tokenized into representations that can be handled by transformers; for the case of the sentence, each word is a token. The source sentence is tokenized again, but this time passed through the visual hallucination transformer, outputting a hallucination, a discrete image representation of the sentence. The researchers incorporated an autoregression that compares the ground-truth and hallucinated representations for congruency — e.g., homonyms: a reference to an animal “bat” isn’t hallucinated as a baseball bat. The hallucination transformer then uses the difference between them to optimize its predictions and visual output, making sure the context is consistent.

      The two sets of tokens are then simultaneously passed through the multimodal translation transformer, each containing the sentence representation and either the hallucinated or ground-truth image. The tokenized text translation outputs are compared with the goal of being similar to each other and to the target sentence in another language. Any differences are then relayed back to the translation transformer for further optimization.

      For testing, the ground-truth image stream drops off, since images likely wouldn’t be available in everyday scenarios.

      “To the best of our knowledge, we haven’t seen any work which actually uses a hallucination transformer jointly with a multimodal translation system to improve machine translation performance,” says Panda.

      Visualizing the target text

      To test their method, the team put VALHALLA up against other state-of-the-art multimodal and text-only translation methods. They used public benchmark datasets containing ground-truth images with source sentences, and a dataset for translating text-only news articles. The researchers measured its performance over 13 tasks, ranging from translation on well-resourced languages (like English, German, and French), under-resourced languages (like English to Romanian) and non-English (like Spanish to French). The group also tested varying transformer model sizes, how accuracy changes with the sentence length, and translation under limited textual context, where portions of the text were hidden from the machine translators.

      The team observed significant improvements over text-only translation methods, improving data efficiency, and that smaller models performed better than the larger base model. As sentences became longer, VALHALLA’s performance over other methods grew, which the researchers attributed to the addition of more ambiguous words. In cases where part of the sentence was masked, VALHALLA could recover and translate the original text, which the team found surprising.

      Further unexpected findings arose: “Where there weren’t as many training [image and] text pairs, [like for under-resourced languages], improvements were more significant, which indicates that grounding in images helps in low-data regimes,” says Kim. “Another thing that was quite surprising to me was this improved performance, even on types of text that aren’t necessarily easily connectable to images. For example, maybe it’s not so surprising if this helps in translating visually salient sentences, like the ‘there is a red car in front of the house.’ [However], even in text-only [news article] domains, the approach was able to improve upon text-only systems.”

      While VALHALLA performs well, the researchers note that it does have limitations, requiring pairs of sentences to be annotated with an image, which could make it more expensive to obtain. It also performs better in its ground domain and not the text-only news articles. Moreover, Kim and Panda note, a technique like VALHALLA is still a black box, with the assumption that hallucinated images are providing helpful information, and the team plans to investigate what and how the model is learning in order to validate their methods.

      In the future, the team plans to explore other means of improving translation. “Here, we only focus on images, but there are other types of a multimodal information — for example, speech, video or touch, or other sensory modalities,” says Panda. “We believe such multimodal grounding can lead to even more efficient machine translation models, potentially benefiting translation across many low-resource languages spoken in the world.”

      This research was supported, in part, by the MIT-IBM Watson AI Lab and the National Science Foundation. More

    • 50 Shares149 Views

      in Data Management & Statistics

      In bias we trust?

      by

      When the stakes are high, machine-learning models are sometimes used to aid human decision-makers. For instance, a model could predict which law school applicants are most likely to pass the bar exam to help an admissions officer determine which students should be accepted.

      These models often have millions of parameters, so how they make predictions is nearly impossible for researchers to fully understand, let alone an admissions officer with no machine-learning experience. Researchers sometimes employ explanation methods that mimic a larger model by creating simple approximations of its predictions. These approximations, which are far easier to understand, help users determine whether to trust the model’s predictions.

      But are these explanation methods fair? If an explanation method provides better approximations for men than for women, or for white people than for Black people, it may encourage users to trust the model’s predictions for some people but not for others.

      MIT researchers took a hard look at the fairness of some widely used explanation methods. They found that the approximation quality of these explanations can vary dramatically between subgroups and that the quality is often significantly lower for minoritized subgroups.

      In practice, this means that if the approximation quality is lower for female applicants, there is a mismatch between the explanations and the model’s predictions that could lead the admissions officer to wrongly reject more women than men.

      Once the MIT researchers saw how pervasive these fairness gaps are, they tried several techniques to level the playing field. They were able to shrink some gaps, but couldn’t eradicate them.

      “What this means in the real-world is that people might incorrectly trust predictions more for some subgroups than for others. So, improving explanation models is important, but communicating the details of these models to end users is equally important. These gaps exist, so users may want to adjust their expectations as to what they are getting when they use these explanations,” says lead author Aparna Balagopalan, a graduate student in the Healthy ML group of the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL).

      Balagopalan wrote the paper with CSAIL graduate students Haoran Zhang and Kimia Hamidieh; CSAIL postdoc Thomas Hartvigsen; Frank Rudzicz, associate professor of computer science at the University of Toronto; and senior author Marzyeh Ghassemi, an assistant professor and head of the Healthy ML Group. The research will be presented at the ACM Conference on Fairness, Accountability, and Transparency.

      High fidelity

      Simplified explanation models can approximate predictions of a more complex machine-learning model in a way that humans can grasp. An effective explanation model maximizes a property known as fidelity, which measures how well it matches the larger model’s predictions.

      Rather than focusing on average fidelity for the overall explanation model, the MIT researchers studied fidelity for subgroups of people in the model’s dataset. In a dataset with men and women, the fidelity should be very similar for each group, and both groups should have fidelity close to that of the overall explanation model.

      “When you are just looking at the average fidelity across all instances, you might be missing out on artifacts that could exist in the explanation model,” Balagopalan says.

      They developed two metrics to measure fidelity gaps, or disparities in fidelity between subgroups. One is the difference between the average fidelity across the entire explanation model and the fidelity for the worst-performing subgroup. The second calculates the absolute difference in fidelity between all possible pairs of subgroups and then computes the average.

      With these metrics, they searched for fidelity gaps using two types of explanation models that were trained on four real-world datasets for high-stakes situations, such as predicting whether a patient dies in the ICU, whether a defendant reoffends, or whether a law school applicant will pass the bar exam. Each dataset contained protected attributes, like the sex and race of individual people. Protected attributes are features that may not be used for decisions, often due to laws or organizational policies. The definition for these can vary based on the task specific to each decision setting.

      The researchers found clear fidelity gaps for all datasets and explanation models. The fidelity for disadvantaged groups was often much lower, up to 21 percent in some instances. The law school dataset had a fidelity gap of 7 percent between race subgroups, meaning the approximations for some subgroups were wrong 7 percent more often on average. If there are 10,000 applicants from these subgroups in the dataset, for example, a significant portion could be wrongly rejected, Balagopalan explains.

      “I was surprised by how pervasive these fidelity gaps are in all the datasets we evaluated. It is hard to overemphasize how commonly explanations are used as a ‘fix’ for black-box machine-learning models. In this paper, we are showing that the explanation methods themselves are imperfect approximations that may be worse for some subgroups,” says Ghassemi.

      Narrowing the gaps

      After identifying fidelity gaps, the researchers tried some machine-learning approaches to fix them. They trained the explanation models to identify regions of a dataset that could be prone to low fidelity and then focus more on those samples. They also tried using balanced datasets with an equal number of samples from all subgroups.

      These robust training strategies did reduce some fidelity gaps, but they didn’t eliminate them.

      The researchers then modified the explanation models to explore why fidelity gaps occur in the first place. Their analysis revealed that an explanation model might indirectly use protected group information, like sex or race, that it could learn from the dataset, even if group labels are hidden.

      They want to explore this conundrum more in future work. They also plan to further study the implications of fidelity gaps in the context of real-world decision making.

      Balagopalan is excited to see that concurrent work on explanation fairness from an independent lab has arrived at similar conclusions, highlighting the importance of understanding this problem well.

      As she looks to the next phase in this research, she has some words of warning for machine-learning users.

      “Choose the explanation model carefully. But even more importantly, think carefully about the goals of using an explanation model and who it eventually affects,” she says.

      This work was funded, in part, by the MIT-IBM Watson AI Lab, the Quanta Research Institute, a Canadian Institute for Advanced Research AI Chair, and Microsoft Research. More

    • 113 Shares169 Views

      in Data Management & Statistics

      Artificial intelligence predicts patients’ race from their medical images

      by

      The miseducation of algorithms is a critical problem; when artificial intelligence mirrors unconscious thoughts, racism, and biases of the humans who generated these algorithms, it can lead to serious harm. Computer programs, for example, have wrongly flagged Black defendants as twice as likely to reoffend as someone who’s white. When an AI used cost as a proxy for health needs, it falsely named Black patients as healthier than equally sick white ones, as less money was spent on them. Even AI used to write a play relied on using harmful stereotypes for casting. 

      Removing sensitive features from the data seems like a viable tweak. But what happens when it’s not enough? 

      Examples of bias in natural language processing are boundless — but MIT scientists have investigated another important, largely underexplored modality: medical images. Using both private and public datasets, the team found that AI can accurately predict self-reported race of patients from medical images alone. Using imaging data of chest X-rays, limb X-rays, chest CT scans, and mammograms, the team trained a deep learning model to identify race as white, Black, or Asian — even though the images themselves contained no explicit mention of the patient’s race. This is a feat even the most seasoned physicians cannot do, and it’s not clear how the model was able to do this. 

      In an attempt to tease out and make sense of the enigmatic “how” of it all, the researchers ran a slew of experiments. To investigate possible mechanisms of race detection, they looked at variables like differences in anatomy, bone density, resolution of images — and many more, and the models still prevailed with high ability to detect race from chest X-rays. “These results were initially confusing, because the members of our research team could not come anywhere close to identifying a good proxy for this task,” says paper co-author Marzyeh Ghassemi, an assistant professor in the MIT Department of Electrical Engineering and Computer Science and the Institute for Medical Engineering and Science (IMES), who is an affiliate of the Computer Science and Artificial Intelligence Laboratory (CSAIL) and of the MIT Jameel Clinic. “Even when you filter medical images past where the images are recognizable as medical images at all, deep models maintain a very high performance. That is concerning because superhuman capacities are generally much more difficult to control, regulate, and prevent from harming people.”

      In a clinical setting, algorithms can help tell us whether a patient is a candidate for chemotherapy, dictate the triage of patients, or decide if a movement to the ICU is necessary. “We think that the algorithms are only looking at vital signs or laboratory tests, but it’s possible they’re also looking at your race, ethnicity, sex, whether you’re incarcerated or not — even if all of that information is hidden,” says paper co-author Leo Anthony Celi, principal research scientist in IMES at MIT and associate professor of medicine at Harvard Medical School. “Just because you have representation of different groups in your algorithms, that doesn’t guarantee it won’t perpetuate or magnify existing disparities and inequities. Feeding the algorithms with more data with representation is not a panacea. This paper should make us pause and truly reconsider whether we are ready to bring AI to the bedside.” 

      The study, “AI recognition of patient race in medical imaging: a modeling study,” was published in Lancet Digital Health on May 11. Celi and Ghassemi wrote the paper alongside 20 other authors in four countries.

      To set up the tests, the scientists first showed that the models were able to predict race across multiple imaging modalities, various datasets, and diverse clinical tasks, as well as across a range of academic centers and patient populations in the United States. They used three large chest X-ray datasets, and tested the model on an unseen subset of the dataset used to train the model and a completely different one. Next, they trained the racial identity detection models for non-chest X-ray images from multiple body locations, including digital radiography, mammography, lateral cervical spine radiographs, and chest CTs to see whether the model’s performance was limited to chest X-rays. 

      The team covered many bases in an attempt to explain the model’s behavior: differences in physical characteristics between different racial groups (body habitus, breast density), disease distribution (previous studies have shown that Black patients have a higher incidence for health issues like cardiac disease), location-specific or tissue specific differences, effects of societal bias and environmental stress, the ability of deep learning systems to detect race when multiple demographic and patient factors were combined, and if specific image regions contributed to recognizing race. 

      What emerged was truly staggering: The ability of the models to predict race from diagnostic labels alone was much lower than the chest X-ray image-based models. 

      For example, the bone density test used images where the thicker part of the bone appeared white, and the thinner part appeared more gray or translucent. Scientists assumed that since Black people generally have higher bone mineral density, the color differences helped the AI models to detect race. To cut that off, they clipped the images with a filter, so the model couldn’t color differences. It turned out that cutting off the color supply didn’t faze the model — it still could accurately predict races. (The “Area Under the Curve” value, meaning the measure of the accuracy of a quantitative diagnostic test, was 0.94–0.96). As such, the learned features of the model appeared to rely on all regions of the image, meaning that controlling this type of algorithmic behavior presents a messy, challenging problem. 

      The scientists acknowledge limited availability of racial identity labels, which caused them to focus on Asian, Black, and white populations, and that their ground truth was a self-reported detail. Other forthcoming work will include potentially looking at isolating different signals before image reconstruction, because, as with bone density experiments, they couldn’t account for residual bone tissue that was on the images. 

      Notably, other work by Ghassemi and Celi led by MIT student Hammaad Adam has found that models can also identify patient self-reported race from clinical notes even when those notes are stripped of explicit indicators of race. Just as in this work, human experts are not able to accurately predict patient race from the same redacted clinical notes.

      “We need to bring social scientists into the picture. Domain experts, which are usually the clinicians, public health practitioners, computer scientists, and engineers are not enough. Health care is a social-cultural problem just as much as it’s a medical problem. We need another group of experts to weigh in and to provide input and feedback on how we design, develop, deploy, and evaluate these algorithms,” says Celi. “We need to also ask the data scientists, before any exploration of the data, are there disparities? Which patient groups are marginalized? What are the drivers of those disparities? Is it access to care? Is it from the subjectivity of the care providers? If we don’t understand that, we won’t have a chance of being able to identify the unintended consequences of the algorithms, and there’s no way we’ll be able to safeguard the algorithms from perpetuating biases.”

      “The fact that algorithms ‘see’ race, as the authors convincingly document, can be dangerous. But an important and related fact is that, when used carefully, algorithms can also work to counter bias,” says Ziad Obermeyer, associate professor at the University of California at Berkeley, whose research focuses on AI applied to health. “In our own work, led by computer scientist Emma Pierson at Cornell, we show that algorithms that learn from patients’ pain experiences can find new sources of knee pain in X-rays that disproportionately affect Black patients — and are disproportionately missed by radiologists. So just like any tool, algorithms can be a force for evil or a force for good — which one depends on us, and the choices we make when we build algorithms.”

      The work is supported, in part, by the National Institutes of Health. More

    • 50 Shares109 Views

      in Data Management & Statistics

      Living better with algorithms

      by

      Laboratory for Information and Decision Systems (LIDS) student Sarah Cen remembers the lecture that sent her down the track to an upstream question.

      At a talk on ethical artificial intelligence, the speaker brought up a variation on the famous trolley problem, which outlines a philosophical choice between two undesirable outcomes.

      The speaker’s scenario: Say a self-driving car is traveling down a narrow alley with an elderly woman walking on one side and a small child on the other, and no way to thread between both without a fatality. Who should the car hit?

      Then the speaker said: Let’s take a step back. Is this the question we should even be asking?

      That’s when things clicked for Cen. Instead of considering the point of impact, a self-driving car could have avoided choosing between two bad outcomes by making a decision earlier on — the speaker pointed out that, when entering the alley, the car could have determined that the space was narrow and slowed to a speed that would keep everyone safe.

      Recognizing that today’s AI safety approaches often resemble the trolley problem, focusing on downstream regulation such as liability after someone is left with no good choices, Cen wondered: What if we could design better upstream and downstream safeguards to such problems? This question has informed much of Cen’s work.

      “Engineering systems are not divorced from the social systems on which they intervene,” Cen says. Ignoring this fact risks creating tools that fail to be useful when deployed or, more worryingly, that are harmful.

      Cen arrived at LIDS in 2018 via a slightly roundabout route. She first got a taste for research during her undergraduate degree at Princeton University, where she majored in mechanical engineering. For her master’s degree, she changed course, working on radar solutions in mobile robotics (primarily for self-driving cars) at Oxford University. There, she developed an interest in AI algorithms, curious about when and why they misbehave. So, she came to MIT and LIDS for her doctoral research, working with Professor Devavrat Shah in the Department of Electrical Engineering and Computer Science, for a stronger theoretical grounding in information systems.

      Auditing social media algorithms

      Together with Shah and other collaborators, Cen has worked on a wide range of projects during her time at LIDS, many of which tie directly to her interest in the interactions between humans and computational systems. In one such project, Cen studies options for regulating social media. Her recent work provides a method for translating human-readable regulations into implementable audits.

      To get a sense of what this means, suppose that regulators require that any public health content — for example, on vaccines — not be vastly different for politically left- and right-leaning users. How should auditors check that a social media platform complies with this regulation? Can a platform be made to comply with the regulation without damaging its bottom line? And how does compliance affect the actual content that users do see?

      Designing an auditing procedure is difficult in large part because there are so many stakeholders when it comes to social media. Auditors have to inspect the algorithm without accessing sensitive user data. They also have to work around tricky trade secrets, which can prevent them from getting a close look at the very algorithm that they are auditing because these algorithms are legally protected. Other considerations come into play as well, such as balancing the removal of misinformation with the protection of free speech.

      To meet these challenges, Cen and Shah developed an auditing procedure that does not need more than black-box access to the social media algorithm (which respects trade secrets), does not remove content (which avoids issues of censorship), and does not require access to users (which preserves users’ privacy).

      In their design process, the team also analyzed the properties of their auditing procedure, finding that it ensures a desirable property they call decision robustness. As good news for the platform, they show that a platform can pass the audit without sacrificing profits. Interestingly, they also found the audit naturally incentivizes the platform to show users diverse content, which is known to help reduce the spread of misinformation, counteract echo chambers, and more.

      Who gets good outcomes and who gets bad ones?

      In another line of research, Cen looks at whether people can receive good long-term outcomes when they not only compete for resources, but also don’t know upfront what resources are best for them.

      Some platforms, such as job-search platforms or ride-sharing apps, are part of what is called a matching market, which uses an algorithm to match one set of individuals (such as workers or riders) with another (such as employers or drivers). In many cases, individuals have matching preferences that they learn through trial and error. In labor markets, for example, workers learn their preferences about what kinds of jobs they want, and employers learn their preferences about the qualifications they seek from workers.

      But learning can be disrupted by competition. If workers with a particular background are repeatedly denied jobs in tech because of high competition for tech jobs, for instance, they may never get the knowledge they need to make an informed decision about whether they want to work in tech. Similarly, tech employers may never see and learn what these workers could do if they were hired.

      Cen’s work examines this interaction between learning and competition, studying whether it is possible for individuals on both sides of the matching market to walk away happy.

      Modeling such matching markets, Cen and Shah found that it is indeed possible to get to a stable outcome (workers aren’t incentivized to leave the matching market), with low regret (workers are happy with their long-term outcomes), fairness (happiness is evenly distributed), and high social welfare.

      Interestingly, it’s not obvious that it’s possible to get stability, low regret, fairness, and high social welfare simultaneously.  So another important aspect of the research was uncovering when it is possible to achieve all four criteria at once and exploring the implications of those conditions.

      What is the effect of X on Y?

      For the next few years, though, Cen plans to work on a new project, studying how to quantify the effect of an action X on an outcome Y when it’s expensive — or impossible — to measure this effect, focusing in particular on systems that have complex social behaviors.

      For instance, when Covid-19 cases surged in the pandemic, many cities had to decide what restrictions to adopt, such as mask mandates, business closures, or stay-home orders. They had to act fast and balance public health with community and business needs, public spending, and a host of other considerations.

      Typically, in order to estimate the effect of restrictions on the rate of infection, one might compare the rates of infection in areas that underwent different interventions. If one county has a mask mandate while its neighboring county does not, one might think comparing the counties’ infection rates would reveal the effectiveness of mask mandates. 

      But of course, no county exists in a vacuum. If, for instance, people from both counties gather to watch a football game in the maskless county every week, people from both counties mix. These complex interactions matter, and Sarah plans to study questions of cause and effect in such settings.

      “We’re interested in how decisions or interventions affect an outcome of interest, such as how criminal justice reform affects incarceration rates or how an ad campaign might change the public’s behaviors,” Cen says.

      Cen has also applied the principles of promoting inclusivity to her work in the MIT community.

      As one of three co-presidents of the Graduate Women in MIT EECS student group, she helped organize the inaugural GW6 research summit featuring the research of women graduate students — not only to showcase positive role models to students, but also to highlight the many successful graduate women at MIT who are not to be underestimated.

      Whether in computing or in the community, a system taking steps to address bias is one that enjoys legitimacy and trust, Cen says. “Accountability, legitimacy, trust — these principles play crucial roles in society and, ultimately, will determine which systems endure with time.”  More