Human-computer interaction

Subterms

    More stories

    • 138 Shares129 Views

      in Data Management & Statistics

      Study: AI models fail to reproduce human judgements about rule violations

      by

      In an effort to improve fairness or reduce backlogs, machine-learning models are sometimes designed to mimic human decision making, such as deciding whether social media posts violate toxic content policies.

      But researchers from MIT and elsewhere have found that these models often do not replicate human decisions about rule violations. If models are not trained with the right data, they are likely to make different, often harsher judgements than humans would.

      In this case, the “right” data are those that have been labeled by humans who were explicitly asked whether items defy a certain rule. Training involves showing a machine-learning model millions of examples of this “normative data” so it can learn a task.

      But data used to train machine-learning models are typically labeled descriptively — meaning humans are asked to identify factual features, such as, say, the presence of fried food in a photo. If “descriptive data” are used to train models that judge rule violations, such as whether a meal violates a school policy that prohibits fried food, the models tend to over-predict rule violations.

      This drop in accuracy could have serious implications in the real world. For instance, if a descriptive model is used to make decisions about whether an individual is likely to reoffend, the researchers’ findings suggest it may cast stricter judgements than a human would, which could lead to higher bail amounts or longer criminal sentences.

      “I think most artificial intelligence/machine-learning researchers assume that the human judgements in data and labels are biased, but this result is saying something worse. These models are not even reproducing already-biased human judgments because the data they’re being trained on has a flaw: Humans would label the features of images and text differently if they knew those features would be used for a judgment. This has huge ramifications for machine learning systems in human processes,” says Marzyeh Ghassemi, an assistant professor and head of the Healthy ML Group in the Computer Science and Artificial Intelligence Laboratory (CSAIL).

      Ghassemi is senior author of a new paper detailing these findings, which was published today in Science Advances. Joining her on the paper are lead author Aparna Balagopalan, an electrical engineering and computer science graduate student; David Madras, a graduate student at the University of Toronto; David H. Yang, a former graduate student who is now co-founder of ML Estimation; Dylan Hadfield-Menell, an MIT assistant professor; and Gillian K. Hadfield, Schwartz Reisman Chair in Technology and Society and professor of law at the University of Toronto.

      Labeling discrepancy

      This study grew out of a different project that explored how a machine-learning model can justify its predictions. As they gathered data for that study, the researchers noticed that humans sometimes give different answers if they are asked to provide descriptive or normative labels about the same data.

      To gather descriptive labels, researchers ask labelers to identify factual features — does this text contain obscene language? To gather normative labels, researchers give labelers a rule and ask if the data violates that rule — does this text violate the platform’s explicit language policy?

      Surprised by this finding, the researchers launched a user study to dig deeper. They gathered four datasets to mimic different policies, such as a dataset of dog images that could be in violation of an apartment’s rule against aggressive breeds. Then they asked groups of participants to provide descriptive or normative labels.

      In each case, the descriptive labelers were asked to indicate whether three factual features were present in the image or text, such as whether the dog appears aggressive. Their responses were then used to craft judgements. (If a user said a photo contained an aggressive dog, then the policy was violated.) The labelers did not know the pet policy. On the other hand, normative labelers were given the policy prohibiting aggressive dogs, and then asked whether it had been violated by each image, and why.

      The researchers found that humans were significantly more likely to label an object as a violation in the descriptive setting. The disparity, which they computed using the absolute difference in labels on average, ranged from 8 percent on a dataset of images used to judge dress code violations to 20 percent for the dog images.

      “While we didn’t explicitly test why this happens, one hypothesis is that maybe how people think about rule violations is different from how they think about descriptive data. Generally, normative decisions are more lenient,” Balagopalan says.

      Yet data are usually gathered with descriptive labels to train a model for a particular machine-learning task. These data are often repurposed later to train different models that perform normative judgements, like rule violations.

      Training troubles

      To study the potential impacts of repurposing descriptive data, the researchers trained two models to judge rule violations using one of their four data settings. They trained one model using descriptive data and the other using normative data, and then compared their performance.

      They found that if descriptive data are used to train a model, it will underperform a model trained to perform the same judgements using normative data. Specifically, the descriptive model is more likely to misclassify inputs by falsely predicting a rule violation. And the descriptive model’s accuracy was even lower when classifying objects that human labelers disagreed about.

      “This shows that the data do really matter. It is important to match the training context to the deployment context if you are training models to detect if a rule has been violated,” Balagopalan says.

      It can be very difficult for users to determine how data have been gathered; this information can be buried in the appendix of a research paper or not revealed by a private company, Ghassemi says.

      Improving dataset transparency is one way this problem could be mitigated. If researchers know how data were gathered, then they know how those data should be used. Another possible strategy is to fine-tune a descriptively trained model on a small amount of normative data. This idea, known as transfer learning, is something the researchers want to explore in future work.

      They also want to conduct a similar study with expert labelers, like doctors or lawyers, to see if it leads to the same label disparity.

      “The way to fix this is to transparently acknowledge that if we want to reproduce human judgment, we must only use data that were collected in that setting. Otherwise, we are going to end up with systems that are going to have extremely harsh moderations, much harsher than what humans would do. Humans would see nuance or make another distinction, whereas these models don’t,” Ghassemi says.

      This research was funded, in part, by the Schwartz Reisman Institute for Technology and Society, Microsoft Research, the Vector Institute, and a Canada Research Council Chain. More

    • 75 Shares119 Views

      in Data Management & Statistics

      Efficient technique improves machine-learning models’ reliability

      by

      Powerful machine-learning models are being used to help people tackle tough problems such as identifying disease in medical images or detecting road obstacles for autonomous vehicles. But machine-learning models can make mistakes, so in high-stakes settings it’s critical that humans know when to trust a model’s predictions.

      Uncertainty quantification is one tool that improves a model’s reliability; the model produces a score along with the prediction that expresses a confidence level that the prediction is correct. While uncertainty quantification can be useful, existing methods typically require retraining the entire model to give it that ability. Training involves showing a model millions of examples so it can learn a task. Retraining then requires millions of new data inputs, which can be expensive and difficult to obtain, and also uses huge amounts of computing resources.

      Researchers at MIT and the MIT-IBM Watson AI Lab have now developed a technique that enables a model to perform more effective uncertainty quantification, while using far fewer computing resources than other methods, and no additional data. Their technique, which does not require a user to retrain or modify a model, is flexible enough for many applications.

      The technique involves creating a simpler companion model that assists the original machine-learning model in estimating uncertainty. This smaller model is designed to identify different types of uncertainty, which can help researchers drill down on the root cause of inaccurate predictions.

      “Uncertainty quantification is essential for both developers and users of machine-learning models. Developers can utilize uncertainty measurements to help develop more robust models, while for users, it can add another layer of trust and reliability when deploying models in the real world. Our work leads to a more flexible and practical solution for uncertainty quantification,” says Maohao Shen, an electrical engineering and computer science graduate student and lead author of a paper on this technique.

      Shen wrote the paper with Yuheng Bu, a former postdoc in the Research Laboratory of Electronics (RLE) who is now an assistant professor at the University of Florida; Prasanna Sattigeri, Soumya Ghosh, and Subhro Das, research staff members at the MIT-IBM Watson AI Lab; and senior author Gregory Wornell, the Sumitomo Professor in Engineering who leads the Signals, Information, and Algorithms Laboratory RLE and is a member of the MIT-IBM Watson AI Lab. The research will be presented at the AAAI Conference on Artificial Intelligence.

      Quantifying uncertainty

      In uncertainty quantification, a machine-learning model generates a numerical score with each output to reflect its confidence in that prediction’s accuracy. Incorporating uncertainty quantification by building a new model from scratch or retraining an existing model typically requires a large amount of data and expensive computation, which is often impractical. What’s more, existing methods sometimes have the unintended consequence of degrading the quality of the model’s predictions.

      The MIT and MIT-IBM Watson AI Lab researchers have thus zeroed in on the following problem: Given a pretrained model, how can they enable it to perform effective uncertainty quantification?

      They solve this by creating a smaller and simpler model, known as a metamodel, that attaches to the larger, pretrained model and uses the features that larger model has already learned to help it make uncertainty quantification assessments.

      “The metamodel can be applied to any pretrained model. It is better to have access to the internals of the model, because we can get much more information about the base model, but it will also work if you just have a final output. It can still predict a confidence score,” Sattigeri says.

      They design the metamodel to produce the uncertainty quantification output using a technique that includes both types of uncertainty: data uncertainty and model uncertainty. Data uncertainty is caused by corrupted data or inaccurate labels and can only be reduced by fixing the dataset or gathering new data. In model uncertainty, the model is not sure how to explain the newly observed data and might make incorrect predictions, most likely because it hasn’t seen enough similar training examples. This issue is an especially challenging but common problem when models are deployed. In real-world settings, they often encounter data that are different from the training dataset.

      “Has the reliability of your decisions changed when you use the model in a new setting? You want some way to have confidence in whether it is working in this new regime or whether you need to collect training data for this particular new setting,” Wornell says.

      Validating the quantification

      Once a model produces an uncertainty quantification score, the user still needs some assurance that the score itself is accurate. Researchers often validate accuracy by creating a smaller dataset, held out from the original training data, and then testing the model on the held-out data. However, this technique does not work well in measuring uncertainty quantification because the model can achieve good prediction accuracy while still being over-confident, Shen says.

      They created a new validation technique by adding noise to the data in the validation set — this noisy data is more like out-of-distribution data that can cause model uncertainty. The researchers use this noisy dataset to evaluate uncertainty quantifications.

      They tested their approach by seeing how well a meta-model could capture different types of uncertainty for various downstream tasks, including out-of-distribution detection and misclassification detection. Their method not only outperformed all the baselines in each downstream task but also required less training time to achieve those results.

      This technique could help researchers enable more machine-learning models to effectively perform uncertainty quantification, ultimately aiding users in making better decisions about when to trust predictions.

      Moving forward, the researchers want to adapt their technique for newer classes of models, such as large language models that have a different structure than a traditional neural network, Shen says.

      The work was funded, in part, by the MIT-IBM Watson AI Lab and the U.S. National Science Foundation. More

    • 63 Shares149 Views

      in Data Management & Statistics

      Meet the 2022-23 Accenture Fellows

      by

      Launched in October 2020, the MIT and Accenture Convergence Initiative for Industry and Technology underscores the ways in which industry and technology can collaborate to spur innovation. The five-year initiative aims to achieve its mission through research, education, and fellowships. To that end, Accenture has once again awarded five annual fellowships to MIT graduate students working on research in industry and technology convergence who are underrepresented, including by race, ethnicity, and gender.This year’s Accenture Fellows work across research areas including telemonitoring, human-computer interactions, operations research,  AI-mediated socialization, and chemical transformations. Their research covers a wide array of projects, including designing low-power processing hardware for telehealth applications; applying machine learning to streamline and improve business operations; improving mental health care through artificial intelligence; and using machine learning to understand the environmental and health consequences of complex chemical reactions.As part of the application process, student nominations were invited from each unit within the School of Engineering, as well as from the Institute’s four other schools and the MIT Schwarzman College of Computing. Five exceptional students were selected as fellows for the initiative’s third year.Drew Buzzell is a doctoral candidate in electrical engineering and computer science whose research concerns telemonitoring, a fast-growing sphere of telehealth in which information is collected through internet-of-things (IoT) connected devices and transmitted to the cloud. Currently, the high volume of information involved in telemonitoring — and the time and energy costs of processing it — make data analysis difficult. Buzzell’s work is focused on edge computing, a new computing architecture that seeks to address these challenges by managing data closer to the source, in a distributed network of IoT devices. Buzzell earned his BS in physics and engineering science and his MS in engineering science from the Pennsylvania State University.

      Mengying (Cathy) Fang is a master’s student in the MIT School of Architecture and Planning. Her research focuses on augmented reality and virtual reality platforms. Fang is developing novel sensors and machine components that combine computation, materials science, and engineering. Moving forward, she will explore topics including soft robotics techniques that could be integrated with clothes and wearable devices and haptic feedback in order to develop interactions with digital objects. Fang earned a BS in mechanical engineering and human-computer interaction from Carnegie Mellon University.

      Xiaoyue Gong is a doctoral candidate in operations research at the MIT Sloan School of Management. Her research aims to harness the power of machine learning and data science to reduce inefficiencies in the operation of businesses, organizations, and society. With the support of an Accenture Fellowship, Gong seeks to find solutions to operational problems by designing reinforcement learning methods and other machine learning techniques to embedded operational problems. Gong earned a BS in honors mathematics and interactive media arts from New York University.

      Ruby Liu is a doctoral candidate in medical engineering and medical physics. Their research addresses the growing pandemic of loneliness among older adults, which leads to poor health outcomes and presents particularly high risks for historically marginalized people, including members of the LGBTQ+ community and people of color. Liu is designing a network of interconnected AI agents that foster connections between user and agent, offering mental health care while strengthening and facilitating human-human connections. Liu received a BS in biomedical engineering from Johns Hopkins University.

      Joules Provenzano is a doctoral candidate in chemical engineering. Their work integrates machine learning and liquid chromatography-high resolution mass spectrometry (LC-HRMS) to improve our understanding of complex chemical reactions in the environment. As an Accenture Fellow, Provenzano will build upon recent advances in machine learning and LC-HRMS, including novel algorithms for processing real, experimental HR-MS data and new approaches in extracting structure-transformation rules and kinetics. Their research could speed the pace of discovery in the chemical sciences and benefits industries including oil and gas, pharmaceuticals, and agriculture. Provenzano earned a BS in chemical engineering and international and global studies from the Rochester Institute of Technology. More

    • 175 Shares149 Views

      in Data Management & Statistics

      Caspar Hare, Georgia Perakis named associate deans of Social and Ethical Responsibilities of Computing

      by

      Caspar Hare and Georgia Perakis have been appointed the new associate deans of the Social and Ethical Responsibilities of Computing (SERC), a cross-cutting initiative in the MIT Stephen A. Schwarzman College of Computing. Their new roles will take effect on Sept. 1.

      “Infusing social and ethical aspects of computing in academic research and education is a critical component of the college mission,” says Daniel Huttenlocher, dean of the MIT Schwarzman College of Computing and the Henry Ellis Warren Professor of Electrical Engineering and Computer Science. “I look forward to working with Caspar and Georgia on continuing to develop and advance SERC and its reach across MIT. Their complementary backgrounds and their broad connections across MIT will be invaluable to this next chapter of SERC.”

      Caspar Hare

      Hare is a professor of philosophy in the Department of Linguistics and Philosophy. A member of the MIT faculty since 2003, his main interests are in ethics, metaphysics, and epistemology. The general theme of his recent work has been to bring ideas about practical rationality and metaphysics to bear on issues in normative ethics and epistemology. He is the author of two books: “On Myself, and Other, Less Important Subjects” (Princeton University Press 2009), about the metaphysics of perspective, and “The Limits of Kindness” (Oxford University Press 2013), about normative ethics.

      Georgia Perakis

      Perakis is the William F. Pounds Professor of Management and professor of operations research, statistics, and operations management at the MIT Sloan School of Management, where she has been a faculty member since 1998. She investigates the theory and practice of analytics and its role in operations problems and is particularly interested in how to solve complex and practical problems in pricing, revenue management, supply chains, health care, transportation, and energy applications, among other areas. Since 2019, she has been the co-director of the Operations Research Center, an interdepartmental PhD program that jointly reports to MIT Sloan and the MIT Schwarzman College of Computing, a role in which she will remain. Perakis will also assume an associate dean role at MIT Sloan in recognition of her leadership.

      Hare and Perakis succeed David Kaiser, the Germeshausen Professor of the History of Science and professor of physics, and Julie Shah, the H.N. Slater Professor of Aeronautics and Astronautics, who will be stepping down from their roles at the conclusion of their three-year term on Aug. 31.

      “My deepest thanks to Dave and Julie for their tremendous leadership of SERC and contributions to the college as associate deans,” says Huttenlocher.

      SERC impact

      As the inaugural associate deans of SERC, Kaiser and Shah have been responsible for advancing a mission to incorporate humanist, social science, social responsibility, and civic perspectives into MIT’s teaching, research, and implementation of computing. In doing so, they have engaged dozens of faculty members and thousands of students from across MIT during these first three years of the initiative.

      They have brought together people from a broad array of disciplines to collaborate on crafting original materials such as active learning projects, homework assignments, and in-class demonstrations. A collection of these materials was recently published and is now freely available to the world via MIT OpenCourseWare.

      In February 2021, they launched the MIT Case Studies in Social and Ethical Responsibilities of Computing for undergraduate instruction across a range of classes and fields of study. The specially commissioned and peer-reviewed cases are based on original research and are brief by design. Three issues have been published to date and a fourth will be released later this summer. Kaiser will continue to oversee the successful new series as editor.

      Last year, 60 undergraduates, graduate students, and postdocs joined a community of SERC Scholars to help advance SERC efforts in the college. The scholars participate in unique opportunities throughout, such as the summer Experiential Ethics program. A multidisciplinary team of graduate students last winter worked with the instructors and teaching assistants of class 6.036 (Introduction to Machine Learning), MIT’s largest machine learning course, to infuse weekly labs with material covering ethical computing, data and model bias, and fairness in machine learning through SERC.

      Through efforts such as these, SERC has had a substantial impact at MIT and beyond. Over the course of their tenure, Kaiser and Shah have engaged about 80 faculty members, and more than 2,100 students took courses that included new SERC content in the last year alone. SERC’s reach extended well beyond engineering students, with about 500 exposed to SERC content through courses offered in the School of Humanities, Arts, and Social Sciences, the MIT Sloan School of Management, and the School of Architecture and Planning. More

    • 138 Shares169 Views

      in Data Management & Statistics

      A technique to improve both fairness and accuracy in artificial intelligence

      by

      For workers who use machine-learning models to help them make decisions, knowing when to trust a model’s predictions is not always an easy task, especially since these models are often so complex that their inner workings remain a mystery.

      Users sometimes employ a technique, known as selective regression, in which the model estimates its confidence level for each prediction and will reject predictions when its confidence is too low. Then a human can examine those cases, gather additional information, and make a decision about each one manually.

      But while selective regression has been shown to improve the overall performance of a model, researchers at MIT and the MIT-IBM Watson AI Lab have discovered that the technique can have the opposite effect for underrepresented groups of people in a dataset. As the model’s confidence increases with selective regression, its chance of making the right prediction also increases, but this does not always happen for all subgroups.

      For instance, a model suggesting loan approvals might make fewer errors on average, but it may actually make more wrong predictions for Black or female applicants. One reason this can occur is due to the fact that the model’s confidence measure is trained using overrepresented groups and may not be accurate for these underrepresented groups.

      Once they had identified this problem, the MIT researchers developed two algorithms that can remedy the issue. Using real-world datasets, they show that the algorithms reduce performance disparities that had affected marginalized subgroups.

      “Ultimately, this is about being more intelligent about which samples you hand off to a human to deal with. Rather than just minimizing some broad error rate for the model, we want to make sure the error rate across groups is taken into account in a smart way,” says senior MIT author Greg Wornell, the Sumitomo Professor in Engineering in the Department of Electrical Engineering and Computer Science (EECS) who leads the Signals, Information, and Algorithms Laboratory in the Research Laboratory of Electronics (RLE) and is a member of the MIT-IBM Watson AI Lab.

      Joining Wornell on the paper are co-lead authors Abhin Shah, an EECS graduate student, and Yuheng Bu, a postdoc in RLE; as well as Joshua Ka-Wing Lee SM ’17, ScD ’21 and Subhro Das, Rameswar Panda, and Prasanna Sattigeri, research staff members at the MIT-IBM Watson AI Lab. The paper will be presented this month at the International Conference on Machine Learning.

      To predict or not to predict

      Regression is a technique that estimates the relationship between a dependent variable and independent variables. In machine learning, regression analysis is commonly used for prediction tasks, such as predicting the price of a home given its features (number of bedrooms, square footage, etc.) With selective regression, the machine-learning model can make one of two choices for each input — it can make a prediction or abstain from a prediction if it doesn’t have enough confidence in its decision.

      When the model abstains, it reduces the fraction of samples it is making predictions on, which is known as coverage. By only making predictions on inputs that it is highly confident about, the overall performance of the model should improve. But this can also amplify biases that exist in a dataset, which occur when the model does not have sufficient data from certain subgroups. This can lead to errors or bad predictions for underrepresented individuals.

      The MIT researchers aimed to ensure that, as the overall error rate for the model improves with selective regression, the performance for every subgroup also improves. They call this monotonic selective risk.

      “It was challenging to come up with the right notion of fairness for this particular problem. But by enforcing this criteria, monotonic selective risk, we can make sure the model performance is actually getting better across all subgroups when you reduce the coverage,” says Shah.

      Focus on fairness

      The team developed two neural network algorithms that impose this fairness criteria to solve the problem.

      One algorithm guarantees that the features the model uses to make predictions contain all information about the sensitive attributes in the dataset, such as race and sex, that is relevant to the target variable of interest. Sensitive attributes are features that may not be used for decisions, often due to laws or organizational policies. The second algorithm employs a calibration technique to ensure the model makes the same prediction for an input, regardless of whether any sensitive attributes are added to that input.

      The researchers tested these algorithms by applying them to real-world datasets that could be used in high-stakes decision making. One, an insurance dataset, is used to predict total annual medical expenses charged to patients using demographic statistics; another, a crime dataset, is used to predict the number of violent crimes in communities using socioeconomic information. Both datasets contain sensitive attributes for individuals.

      When they implemented their algorithms on top of a standard machine-learning method for selective regression, they were able to reduce disparities by achieving lower error rates for the minority subgroups in each dataset. Moreover, this was accomplished without significantly impacting the overall error rate.

      “We see that if we don’t impose certain constraints, in cases where the model is really confident, it could actually be making more errors, which could be very costly in some applications, like health care. So if we reverse the trend and make it more intuitive, we will catch a lot of these errors. A major goal of this work is to avoid errors going silently undetected,” Sattigeri says.

      The researchers plan to apply their solutions to other applications, such as predicting house prices, student GPA, or loan interest rate, to see if the algorithms need to be calibrated for those tasks, says Shah. They also want to explore techniques that use less sensitive information during the model training process to avoid privacy issues.

      And they hope to improve the confidence estimates in selective regression to prevent situations where the model’s confidence is low, but its prediction is correct. This could reduce the workload on humans and further streamline the decision-making process, Sattigeri says.

      This research was funded, in part, by the MIT-IBM Watson AI Lab and its member companies Boston Scientific, Samsung, and Wells Fargo, and by the National Science Foundation. More

    • 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

    • 125 Shares199 Views

      in Data Management & Statistics

      Making data visualization more accessible for blind and low-vision individuals

      by

      Data visualizations on the web are largely inaccessible for blind and low-vision individuals who use screen readers, an assistive technology that reads on-screen elements as text-to-speech. This excludes millions of people from the opportunity to probe and interpret insights that are often presented through charts, such as election results, health statistics, and economic indicators. 

      When a designer attempts to make a visualization accessible, best practices call for including a few sentences of text that describe the chart and a link to the underlying data table — a far cry from the rich reading experience available to sighted users.

      An interdisciplinary team of researchers from MIT and elsewhere is striving to create screen-reader-friendly data visualizations that offer a similarly rich experience. They prototyped several visualization structures that provide text descriptions at varying levels of detail, enabling a screen-reader user to drill down from high-level data to more detailed information using just a few keystrokes.

      The MIT team embarked on an iterative co-design process with collaborator Daniel Hajas, a researcher at University College London who works with the Global Disability Innovation Hub and lost his sight at age 16. They collaborated to develop prototypes and ran a detailed user study with blind and low-vision individuals to gather feedback.

      “Researchers might see some connections between problems and be aware of potential solutions, but very often they miss it by a little bit. Insights from people who have the lived experience of a certain specific, measurable problem are really important for a lot of disability-related solutions. I think we found a really nice fit,” says Hajas.

      They created a framework to help designers think systematically about how to develop accessible visualizations. In the future, they plan to use their prototypes and design framework to build a user-friendly tool that could convert visualizations into accessible formats.

      MIT collaborators include co-lead authors and Computer Science and Artificial Intelligence Laboratory (CSAIL) graduate students Jonathan Zong, Crystal Lee, and Alan Lundgard, as well as JiWoong Jang, an undergraduate at Carnegie Mellon University who worked on this project during MIT’s Summer Research Program (MSRP), and senior author Arvind Satyanarayan, assistant professor of computer science who leads the Visualization Group in CSAIL. The research paper, which will be presented at the Eurographics Conference on Visualization, won a best paper honorable mention award.

      “Push what is possible”

      The researchers defined three design dimensions as key to making accessible visualizations: structure, navigation, and description. Structure involves arranging the information into a hierarchy. Navigation refers to how the user moves through different levels of detail. Description is how the information is spoken, including how much information is conveyed.

      Using these design dimensions, they developed several visualization prototypes that emphasized ease-of-navigation for screen-reader users. One prototype, known as multiview, enabled individuals to use the up and down arrows to navigate between different levels of information (like the chart title as the top level, the legend as the second level, etc.), and the right and left arrow keys to cycle through information on the same level (such as adjacent scatterplots). Another prototype, known as target, included the same arrow key navigation but also a drop-down menu of key chart locations so the user could quickly jump to an area of interest.

      “Our goal is not just to work within existing standards to make them serviceable. We really set out to do grounded speculation and imagine where we can push what is possible with these existing standards. We didn’t want to limit ourselves to refitting tools that were designed for images,” says Zong.

      They tested these prototypes and an accessible data table, the existing best practice for accessible visualizations, with 13 blind and visually impaired screen-reader users. They asked users to rate each tool on several criteria, including how easy it was to learn and how easy it was to locate data or answer questions.

      “One thing I thought was really interesting was how much people were constantly testing their own hypotheses or trying to make specific patterns as they moved through the visualization. The implication for navigation is that you want to be able to orient yourself within the visualization so you know where the limits are,” says Lee. “Can you accurately and easily know where the walls are in the room you are exploring?”

      Improved insights

      Users said both prototypes enabled them to more rapidly identify patterns in the data. Scrolling from a high level to deeper levels of information helped them gain insights more easily than when browsing the data table, they said. They also enjoyed faster navigation using the menu in the target prototype.

      But the data table got top marks for ease of use.

      “I expected people to be disappointed with the everyday tools when compared to the new prototypes, but they still clung to the data table a bit, likely because of their familiarity with it. That shows that principles like familiarity, learnability, and usability still matter. No matter how ‘good’ our new invention is, if it is not easy enough to learn, people might stick with an older version,” Hajas says.

      Drawing on these insights, the researchers are refining the prototypes and using them to build a software package that can be used with existing design tools to give visualizations an accessible, navigable structure.

      They also want to explore multimodal solutions. Some study participants used different devices together, like screen readers and braille displays, or data sonification tools that convey information using non-speech audio. How these tools can complement each other when applied to a visualization is still an open question, Zong says.

      In the long-run, they hope their work might lead to careful rethinking of web accessibility standards.

      “There is no one-size-fits-all solution for accessibility. While existing standards don’t presume that, they only offer simple approaches, like data tables and alt text. One of the key benefits of our research contribution is that we are proposing a framework — different preferences and data representations are situated at different points in this design space,” says Lundgard.

      “We have been working hard toward reducing the inequities that screen-reader users face when extracting information from online data visualizations for the past few years. So, we are really appreciative of this work and the knowledge that it adds to the existing literature,” says Ather Sharif, a graduate student who researches accessibility and visualization in the labs of professors Jacob Wobbrock and Katharina Reinecke at the Paul G. Allen School of Computer Science and Engineering of the University of Washington at Seattle, and who was not involved with this work.

      “I like to think of it as a movement where we’re all finally coming together and improving the experiences of a demographic that has been largely ignored, especially when presenting data through visualizations. Kudos to Jonathan, Arvind, and their team for this insightful and timely work! I am looking forward to what’s next,” adds Sharif, who is lead author of several recent papers related to accessible data visualizations.

      Amy Bower, a senior scientist in the Department of Physical Oceanography at the Woods Hole Oceanographic Institution who suffers from a degenerative retinal disease and uses a screen reader extensively in her work as a researcher and also for basic living tasks, found the researchers’ explanations of the importance of co-design to be powerful and compelling.  

      “As a blind scientist, I’m constantly searching for effective tools that will allow me to access the information conveyed in data visualizations. The layered approach taken by these researchers, which provides the option to get the ‘big picture’ from the data as well as drill down into the data points themselves, allows the user to choose how they want to explore the data,” says Bower, who also was not involved with this work. “I think the ability to freely explore the data is necessary not just to learn the ‘story’ that the data are telling, but to allow a blind researcher such as myself to formulate the next questions that need to be tackled to advance understanding in any field of study.”

      This work was supported, in part, by the National Science Foundation.   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