Machine learning

Subterms

    More stories

    • 125 Shares179 Views

      in Data Management & Statistics

      Improving predictions of sea level rise for the next century

      by

      When we think of climate change, one of the most dramatic images that comes to mind is the loss of glacial ice. As the Earth warms, these enormous rivers of ice become a casualty of the rising temperatures. But, as ice sheets retreat, they also become an important contributor to one the more dangerous outcomes of climate change: sea-level rise. At MIT, an interdisciplinary team of scientists is determined to improve sea level rise predictions for the next century, in part by taking a closer look at the physics of ice sheets.

      Last month, two research proposals on the topic, led by Brent Minchew, the Cecil and Ida Green Career Development Professor in the Department of Earth, Atmospheric and Planetary Sciences (EAPS), were announced as finalists in the MIT Climate Grand Challenges initiative. Launched in July 2020, Climate Grand Challenges fielded almost 100 project proposals from collaborators across the Institute who heeded the bold charge: to develop research and innovations that will deliver game-changing advances in the world’s efforts to address the climate challenge.

      As finalists, Minchew and his collaborators from the departments of Urban Studies and Planning, Economics, Civil and Environmental Engineering, the Haystack Observatory, and external partners, received $100,000 to develop their research plans. A subset of the 27 proposals tapped as finalists will be announced next month, making up a portfolio of multiyear “flagship” projects receiving additional funding and support.

      One goal of both Minchew proposals is to more fully understand the most fundamental processes that govern rapid changes in glacial ice, and to use that understanding to build next-generation models that are more predictive of ice sheet behavior as they respond to, and influence, climate change.

      “We need to develop more accurate and computationally efficient models that provide testable projections of sea-level rise over the coming decades. To do so quickly, we want to make better and more frequent observations and learn the physics of ice sheets from these data,” says Minchew. “For example, how much stress do you have to apply to ice before it breaks?”

      Currently, Minchew’s Glacier Dynamics and Remote Sensing group uses satellites to observe the ice sheets on Greenland and Antarctica primarily with interferometric synthetic aperture radar (InSAR). But the data are often collected over long intervals of time, which only gives them “before and after” snapshots of big events. By taking more frequent measurements on shorter time scales, such as hours or days, they can get a more detailed picture of what is happening in the ice.

      “Many of the key unknowns in our projections of what ice sheets are going to look like in the future, and how they’re going to evolve, involve the dynamics of glaciers, or our understanding of how the flow speed and the resistances to flow are related,” says Minchew.

      At the heart of the two proposals is the creation of SACOS, the Stratospheric Airborne Climate Observatory System. The group envisions developing solar-powered drones that can fly in the stratosphere for months at a time, taking more frequent measurements using a new lightweight, low-power radar and other high-resolution instrumentation. They also propose air-dropping sensors directly onto the ice, equipped with seismometers and GPS trackers to measure high-frequency vibrations in the ice and pinpoint the motions of its flow.

      How glaciers contribute to sea level rise

      Current climate models predict an increase in sea levels over the next century, but by just how much is still unclear. Estimates are anywhere from 20 centimeters to two meters, which is a large difference when it comes to enacting policy or mitigation. Minchew points out that response measures will be different, depending on which end of the scale it falls toward. If it’s closer to 20 centimeters, coastal barriers can be built to protect low-level areas. But with higher surges, such measures become too expensive and inefficient to be viable, as entire portions of cities and millions of people would have to be relocated.

      “If we’re looking at a future where we could get more than a meter of sea level rise by the end of the century, then we need to know about that sooner rather than later so that we can start to plan and to do our best to prepare for that scenario,” he says.

      There are two ways glaciers and ice sheets contribute to rising sea levels: direct melting of the ice and accelerated transport of ice to the oceans. In Antarctica, warming waters melt the margins of the ice sheets, which tends to reduce the resistive stresses and allow ice to flow more quickly to the ocean. This thinning can also cause the ice shelves to be more prone to fracture, facilitating the calving of icebergs — events which sometimes cause even further acceleration of ice flow.

      Using data collected by SACOS, Minchew and his group can better understand what material properties in the ice allow for fracturing and calving of icebergs, and build a more complete picture of how ice sheets respond to climate forces. 

      “What I want is to reduce and quantify the uncertainties in projections of sea level rise out to the year 2100,” he says.

      From that more complete picture, the team — which also includes economists, engineers, and urban planning specialists — can work on developing predictive models and methods to help communities and governments estimate the costs associated with sea level rise, develop sound infrastructure strategies, and spur engineering innovation.

      Understanding glacier dynamics

      More frequent radar measurements and the collection of higher-resolution seismic and GPS data will allow Minchew and the team to develop a better understanding of the broad category of glacier dynamics — including calving, an important process in setting the rate of sea level rise which is currently not well understood.  

      “Some of what we’re doing is quite similar to what seismologists do,” he says. “They measure seismic waves following an earthquake, or a volcanic eruption, or things of this nature and use those observations to better understand the mechanisms that govern these phenomena.”

      Air-droppable sensors will help them collect information about ice sheet movement, but this method comes with drawbacks — like installation and maintenance, which is difficult to do out on a massive ice sheet that is moving and melting. Also, the instruments can each only take measurements at a single location. Minchew equates it to a bobber in water: All it can tell you is how the bobber moves as the waves disturb it.

      But by also taking continuous radar measurements from the air, Minchew’s team can collect observations both in space and in time. Instead of just watching the bobber in the water, they can effectively make a movie of the waves propagating out, as well as visualize processes like iceberg calving happening in multiple dimensions.

      Once the bobbers are in place and the movies recorded, the next step is developing machine learning algorithms to help analyze all the new data being collected. While this data-driven kind of discovery has been a hot topic in other fields, this is the first time it has been applied to glacier research.

      “We’ve developed this new methodology to ingest this huge amount of data,” he says, “and from that create an entirely new way of analyzing the system to answer these fundamental and critically important questions.”  More

    • 63 Shares129 Views

      in Data Management & Statistics

      Fighting discrimination in mortgage lending

      by

      Although the U.S. Equal Credit Opportunity Act prohibits discrimination in mortgage lending, biases still impact many borrowers. One 2021 Journal of Financial Economics study found that borrowers from minority groups were charged interest rates that were nearly 8 percent higher and were rejected for loans 14 percent more often than those from privileged groups.

      When these biases bleed into machine-learning models that lenders use to streamline decision-making, they can have far-reaching consequences for housing fairness and even contribute to widening the racial wealth gap.

      If a model is trained on an unfair dataset, such as one in which a higher proportion of Black borrowers were denied loans versus white borrowers with the same income, credit score, etc., those biases will affect the model’s predictions when it is applied to real situations. To stem the spread of mortgage lending discrimination, MIT researchers created a process that removes bias in data that are used to train these machine-learning models.

      While other methods try to tackle this bias, the researchers’ technique is new in the mortgage lending domain because it can remove bias from a dataset that has multiple sensitive attributes, such as race and ethnicity, as well as several “sensitive” options for each attribute, such as Black or white, and Hispanic or Latino or non-Hispanic or Latino. Sensitive attributes and options are features that distinguish a privileged group from an underprivileged group.

      The researchers used their technique, which they call DualFair, to train a machine-learning classifier that makes fair predictions of whether borrowers will receive a mortgage loan. When they applied it to mortgage lending data from several U.S. states, their method significantly reduced the discrimination in the predictions while maintaining high accuracy.

      “As Sikh Americans, we deal with bias on a frequent basis and we think it is unacceptable to see that transform to algorithms in real-world applications. For things like mortgage lending and financial systems, it is very important that bias not infiltrate these systems because it can emphasize the gaps that are already in place against certain groups,” says Jashandeep Singh, a senior at Floyd Buchanan High School and co-lead author of the paper with his twin brother, Arashdeep. The Singh brothers were recently accepted into MIT.

      Joining Arashdeep and Jashandeep Singh on the paper are MIT sophomore Ariba Khan and senior author Amar Gupta, a researcher in the Computer Science and Artificial Intelligence Laboratory at MIT, who studies the use of evolving technology to address inequity and other societal issues. The research was recently published online and will appear in a special issue of Machine Learning and Knowledge Extraction.

      Double take

      DualFair tackles two types of bias in a mortgage lending dataset — label bias and selection bias. Label bias occurs when the balance of favorable or unfavorable outcomes for a particular group is unfair. (Black applicants are denied loans more frequently than they should be.) Selection bias is created when data are not representative of the larger population. (The dataset only includes individuals from one neighborhood where incomes are historically low.)

      The DualFair process eliminates label bias by subdividing a dataset into the largest number of subgroups based on combinations of sensitive attributes and options, such as white men who are not Hispanic or Latino, Black women who are Hispanic or Latino, etc.

      By breaking down the dataset into as many subgroups as possible, DualFair can simultaneously address discrimination based on multiple attributes.

      “Researchers have mostly tried to classify biased cases as binary so far. There are multiple parameters to bias, and these multiple parameters have their own impact in different cases. They are not equally weighed. Our method is able to calibrate it much better,” says Gupta.

      After the subgroups have been generated, DualFair evens out the number of borrowers in each subgroup by duplicating individuals from minority groups and deleting individuals from the majority group. DualFair then balances the proportion of loan acceptances and rejections in each subgroup so they match the median in the original dataset before recombining the subgroups.

      DualFair then eliminates selection bias by iterating on each data point to see if discrimination is present. For instance, if an individual is a non-Hispanic or Latino Black woman who was rejected for a loan, the system will adjust her race, ethnicity, and gender one at a time to see if the outcome changes. If this borrower is granted a loan when her race is changed to white, DualFair considers that data point biased and removes it from the dataset.

      Fairness vs. accuracy

      To test DualFair, the researchers used the publicly available Home Mortgage Disclosure Act dataset, which spans 88 percent of all mortgage loans in the U.S. in 2019, and includes 21 features, including race, sex, and ethnicity. They used DualFair to “de-bias” the entire dataset and smaller datasets for six states, and then trained a machine-learning model to predict loan acceptances and rejections.

      After applying DualFair, the fairness of predictions increased while the accuracy level remained high across all states. They used an existing fairness metric known as average odds difference, but it can only measure fairness in one sensitive attribute at a time.

      So, they created their own fairness metric, called alternate world index, that considers bias from multiple sensitive attributes and options as a whole. Using this metric, they found that DualFair increased fairness in predictions for four of the six states while maintaining high accuracy.

      “It is the common belief that if you want to be accurate, you have to give up on fairness, or if you want to be fair, you have to give up on accuracy. We show that we can make strides toward lessening that gap,” Khan says.

      The researchers now want to apply their method to de-bias different types of datasets, such as those that capture health care outcomes, car insurance rates, or job applications. They also plan to address limitations of DualFair, including its instability when there are small amounts of data with multiple sensitive attributes and options.

      While this is only a first step, the researchers are hopeful their work can someday have an impact on mitigating bias in lending and beyond.

      “Technology, very bluntly, works only for a certain group of people. In the mortgage loan domain in particular, African American women have been historically discriminated against. We feel passionate about making sure that systemic racism does not extend to algorithmic models. There is no point in making an algorithm that can automate a process if it doesn’t work for everyone equally,” says Khan.

      This research is supported, in part, by the FinTech@CSAIL initiative. More

    • 88 Shares119 Views

      in Data Management & Statistics

      Security tool guarantees privacy in surveillance footage

      by

      Surveillance cameras have an identity problem, fueled by an inherent tension between utility and privacy. As these powerful little devices have cropped up seemingly everywhere, the use of machine learning tools has automated video content analysis at a massive scale — but with increasing mass surveillance, there are currently no legally enforceable rules to limit privacy invasions. 

      Security cameras can do a lot — they’ve become smarter and supremely more competent than their ghosts of grainy pictures past, the ofttimes “hero tool” in crime media. (“See that little blurry blue blob in the right hand corner of that densely populated corner — we got him!”) Now, video surveillance can help health officials measure the fraction of people wearing masks, enable transportation departments to monitor the density and flow of vehicles, bikes, and pedestrians, and provide businesses with a better understanding of shopping behaviors. But why has privacy remained a weak afterthought? 

      The status quo is to retrofit video with blurred faces or black boxes. Not only does this prevent analysts from asking some genuine queries (e.g., Are people wearing masks?), it also doesn’t always work; the system may miss some faces and leave them unblurred for the world to see. Dissatisfied with this status quo, researchers from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), in collaboration with other institutions, came up with a system to better guarantee privacy in video footage from surveillance cameras. Called “Privid,” the system lets analysts submit video data queries, and adds a little bit of noise (extra data) to the end result to ensure that an individual can’t be identified. The system builds on a formal definition of privacy — “differential privacy” — which allows access to aggregate statistics about private data without revealing personally identifiable information.

      Typically, analysts would just have access to the entire video to do whatever they want with it, but Privid makes sure the video isn’t a free buffet. Honest analysts can get access to the information they need, but that access is restrictive enough that malicious analysts can’t do too much with it. To enable this, rather than running the code over the entire video in one shot, Privid breaks the video into small pieces and runs processing code over each chunk. Instead of getting results back from each piece, the segments are aggregated, and that additional noise is added. (There’s also information on the error bound you’re going to get on your result — maybe a 2 percent error margin, given the extra noisy data added). 

      For example, the code might output the number of people observed in each video chunk, and the aggregation might be the “sum,” to count the total number of people wearing face coverings, or the “average” to estimate the density of crowds. 

      Privid allows analysts to use their own deep neural networks that are commonplace for video analytics today. This gives analysts the flexibility to ask questions that the designers of Privid did not anticipate. Across a variety of videos and queries, Privid was accurate within 79 to 99 percent of a non-private system.

      “We’re at a stage right now where cameras are practically ubiquitous. If there’s a camera on every street corner, every place you go, and if someone could actually process all of those videos in aggregate, you can imagine that entity building a very precise timeline of when and where a person has gone,” says MIT CSAIL PhD student ​​Frank Cangialosi, the lead author on a paper about Privid. “People are already worried about location privacy with GPS — video data in aggregate could capture not only your location history, but also moods, behaviors, and more at each location.” 

      Privid introduces a new notion of “duration-based privacy,” which decouples the definition of privacy from its enforcement — with obfuscation, if your privacy goal is to protect all people, the enforcement mechanism needs to do some work to find the people to protect, which it may or may not do perfectly. With this mechanism, you don’t need to fully specify everything, and you’re not hiding more information than you need to. 

      Let’s say we have a video overlooking a street. Two analysts, Alice and Bob, both claim they want to count the number of people that pass by each hour, so they submit a video processing module and ask for a sum aggregation.

      The first analyst is the city planning department, which hopes to use this information to understand footfall patterns and plan sidewalks for the city. Their model counts people and outputs this count for each video chunk.

      The other analyst is malicious. They hope to identify every time “Charlie” passes by the camera. Their model only looks for Charlie’s face, and outputs a large number if Charlie is present (i.e., the “signal” they’re trying to extract), or zero otherwise. Their hope is that the sum will be non-zero if Charlie was present. 

      From Privid’s perspective, these two queries look identical. It’s hard to reliably determine what their models might be doing internally, or what the analyst hopes to use the data for. This is where the noise comes in. Privid executes both of the queries, and adds the same amount of noise for each. In the first case, because Alice was counting all people, this noise will only have a small impact on the result, but likely won’t impact the usefulness. 

      In the second case, since Bob was looking for a specific signal (Charlie was only visible for a few chunks), the noise is enough to prevent them from knowing if Charlie was there or not. If they see a non-zero result, it might be because Charlie was actually there, or because the model outputs “zero,” but the noise made it non-zero. Privid didn’t need to know anything about when or where Charlie appeared, the system just needed to know a rough upper bound on how long Charlie might appear for, which is easier to specify than figuring out the exact locations, which prior methods rely on. 

      The challenge is determining how much noise to add — Privid wants to add just enough to hide everyone, but not so much that it would be useless for analysts. Adding noise to the data and insisting on queries over time windows means that your result isn’t going to be as accurate as it could be, but the results are still useful while providing better privacy. 

      Cangialosi wrote the paper with Princeton PhD student Neil Agarwal, MIT CSAIL PhD student Venkat Arun, assistant professor at the University of Chicago Junchen Jiang, assistant professor at Rutgers University and former MIT CSAIL postdoc Srinivas Narayana, associate professor at Rutgers University Anand Sarwate, and assistant professor at Princeton University and Ravi Netravali SM ’15, PhD ’18. Cangialosi will present the paper at the USENIX Symposium on Networked Systems Design and Implementation Conference in April in Renton, Washington. 

      This work was partially supported by a Sloan Research Fellowship and National Science Foundation grants. More

    • 125 Shares149 Views

      in Data Management & Statistics

      When it comes to AI, can we ditch the datasets?

      by

      Huge amounts of data are needed to train machine-learning models to perform image classification tasks, such as identifying damage in satellite photos following a natural disaster. However, these data are not always easy to come by. Datasets may cost millions of dollars to generate, if usable data exist in the first place, and even the best datasets often contain biases that negatively impact a model’s performance.

      To circumvent some of the problems presented by datasets, MIT researchers developed a method for training a machine learning model that, rather than using a dataset, uses a special type of machine-learning model to generate extremely realistic synthetic data that can train another model for downstream vision tasks.

      Their results show that a contrastive representation learning model trained using only these synthetic data is able to learn visual representations that rival or even outperform those learned from real data.

      This special machine-learning model, known as a generative model, requires far less memory to store or share than a dataset. Using synthetic data also has the potential to sidestep some concerns around privacy and usage rights that limit how some real data can be distributed. A generative model could also be edited to remove certain attributes, like race or gender, which could address some biases that exist in traditional datasets.

      “We knew that this method should eventually work; we just needed to wait for these generative models to get better and better. But we were especially pleased when we showed that this method sometimes does even better than the real thing,” says Ali Jahanian, a research scientist in the Computer Science and Artificial Intelligence Laboratory (CSAIL) and lead author of the paper.

      Jahanian wrote the paper with CSAIL grad students Xavier Puig and Yonglong Tian, and senior author Phillip Isola, an assistant professor in the Department of Electrical Engineering and Computer Science. The research will be presented at the International Conference on Learning Representations.

      Generating synthetic data

      Once a generative model has been trained on real data, it can generate synthetic data that are so realistic they are nearly indistinguishable from the real thing. The training process involves showing the generative model millions of images that contain objects in a particular class (like cars or cats), and then it learns what a car or cat looks like so it can generate similar objects.

      Essentially by flipping a switch, researchers can use a pretrained generative model to output a steady stream of unique, realistic images that are based on those in the model’s training dataset, Jahanian says.

      But generative models are even more useful because they learn how to transform the underlying data on which they are trained, he says. If the model is trained on images of cars, it can “imagine” how a car would look in different situations — situations it did not see during training — and then output images that show the car in unique poses, colors, or sizes.

      Having multiple views of the same image is important for a technique called contrastive learning, where a machine-learning model is shown many unlabeled images to learn which pairs are similar or different.

      The researchers connected a pretrained generative model to a contrastive learning model in a way that allowed the two models to work together automatically. The contrastive learner could tell the generative model to produce different views of an object, and then learn to identify that object from multiple angles, Jahanian explains.

      “This was like connecting two building blocks. Because the generative model can give us different views of the same thing, it can help the contrastive method to learn better representations,” he says.

      Even better than the real thing

      The researchers compared their method to several other image classification models that were trained using real data and found that their method performed as well, and sometimes better, than the other models.

      One advantage of using a generative model is that it can, in theory, create an infinite number of samples. So, the researchers also studied how the number of samples influenced the model’s performance. They found that, in some instances, generating larger numbers of unique samples led to additional improvements.

      “The cool thing about these generative models is that someone else trained them for you. You can find them in online repositories, so everyone can use them. And you don’t need to intervene in the model to get good representations,” Jahanian says.

      But he cautions that there are some limitations to using generative models. In some cases, these models can reveal source data, which can pose privacy risks, and they could amplify biases in the datasets they are trained on if they aren’t properly audited.

      He and his collaborators plan to address those limitations in future work. Another area they want to explore is using this technique to generate corner cases that could improve machine learning models. Corner cases often can’t be learned from real data. For instance, if researchers are training a computer vision model for a self-driving car, real data wouldn’t contain examples of a dog and his owner running down a highway, so the model would never learn what to do in this situation. Generating that corner case data synthetically could improve the performance of machine learning models in some high-stakes situations.

      The researchers also want to continue improving generative models so they can compose images that are even more sophisticated, he says.

      This research was supported, in part, by the MIT-IBM Watson AI Lab, the United States Air Force Research Laboratory, and the United States Air Force Artificial Intelligence Accelerator. More

    • 113 Shares199 Views

      in Data Management & Statistics

      An “oracle” for predicting the evolution of gene regulation

      by

      Despite the sheer number of genes that each human cell contains, these so-called “coding” DNA sequences comprise just 1 percent of our entire genome. The remaining 99 percent is made up of “non-coding” DNA — which, unlike coding DNA, does not carry the instructions to build proteins.

      One vital function of this non-coding DNA, also called “regulatory” DNA, is to help turn genes on and off, controlling how much (if any) of a protein is made. Over time, as cells replicate their DNA to grow and divide, mutations often crop up in these non-coding regions — sometimes tweaking their function and changing the way they control gene expression. Many of these mutations are trivial, and some are even beneficial. Occasionally, though, they can be associated with increased risk of common diseases, such as Type 2 diabetes, or more life-threatening ones, including cancer.

      To better understand the repercussions of such mutations, researchers have been hard at work on mathematical maps that allow them to look at an organism’s genome, predict which genes will be expressed, and determine how that expression will affect the organism’s observable traits. These maps, called fitness landscapes, were conceptualized roughly a century ago to understand how genetic makeup influences one common measure of organismal fitness in particular: reproductive success. Early fitness landscapes were very simple, often focusing on a limited number of mutations. Much richer datasets are now available, but researchers still require additional tools to characterize and visualize such complex data. This ability would not only facilitate a better understanding of how individual genes have evolved over time, but would also help to predict what sequence and expression changes might occur in the future.

      In a new study published on March 9 in Nature, a team of scientists has developed a framework for studying the fitness landscapes of regulatory DNA. They created a neural network model that, when trained on hundreds of millions of experimental measurements, was capable of predicting how changes to these non-coding sequences in yeast affected gene expression. They also devised a unique way of representing the landscapes in two dimensions, making it easy to understand the past and forecast the future evolution of non-coding sequences in organisms beyond yeast — and even design custom gene expression patterns for gene therapies and industrial applications.

      “We now have an ‘oracle’ that can be queried to ask: What if we tried all possible mutations of this sequence? Or, what new sequence should we design to give us a desired expression?” says Aviv Regev, a professor of biology at MIT (on leave), core member of the Broad Institute of Harvard and MIT (on leave), head of Genentech Research and Early Development, and the study’s senior author. “Scientists can now use the model for their own evolutionary question or scenario, and for other problems like making sequences that control gene expression in desired ways. I am also excited about the possibilities for machine learning researchers interested in interpretability; they can ask their questions in reverse, to better understand the underlying biology.”

      Prior to this study, many researchers had simply trained their models on known mutations (or slight variations thereof) that exist in nature. However, Regev’s team wanted to go a step further by creating their own unbiased models capable of predicting an organism’s fitness and gene expression based on any possible DNA sequence — even sequences they’d never seen before. This would also enable researchers to use such models to engineer cells for pharmaceutical purposes, including new treatments for cancer and autoimmune disorders.

      To accomplish this goal, Eeshit Dhaval Vaishnav, a graduate student at MIT and co-first author; Carl de Boer, now an assistant professor at the University of British Columbia; and their colleagues created a neural network model to predict gene expression. They trained it on a dataset generated by inserting millions of totally random non-coding DNA sequences into yeast, and observing how each random sequence affected gene expression. They focused on a particular subset of non-coding DNA sequences called promoters, which serve as binding sites for proteins that can switch nearby genes on or off.

      “This work highlights what possibilities open up when we design new kinds of experiments to generate the right data to train models,” Regev says. “In the broader sense, I believe these kinds of approaches will be important for many problems — like understanding genetic variants in regulatory regions that confer disease risk in the human genome, but also for predicting the impact of combinations of mutations, or designing new molecules.”

      Regev, Vaishnav, de Boer, and their coauthors went on to test their model’s predictive abilities in a variety of ways, in order to show how it could help demystify the evolutionary past — and possible future — of certain promoters. “Creating an accurate model was certainly an accomplishment, but, to me, it was really just a starting point,” Vaishnav explains.

      First, to determine whether their model could help with synthetic biology applications like producing antibiotics, enzymes, and food, the researchers practiced using it to design promoters that could generate desired expression levels for any gene of interest. They then scoured other scientific papers to identify fundamental evolutionary questions, in order to see if their model could help answer them. The team even went so far as to feed their model a real-world population dataset from one existing study, which contained genetic information from yeast strains around the world. In doing so, they were able to delineate thousands of years of past selection pressures that sculpted the genomes of today’s yeast.

      But, in order to create a powerful tool that could probe any genome, the researchers knew they’d need to find a way to forecast the evolution of non-coding sequences even without such a comprehensive population dataset. To address this goal, Vaishnav and his colleagues devised a computational technique that allowed them to plot the predictions from their framework onto a two-dimensional graph. This helped them show, in a remarkably simple manner, how any non-coding DNA sequence would affect gene expression and fitness, without needing to conduct any time-consuming experiments at the lab bench.

      “One of the unsolved problems in fitness landscapes was that we didn’t have an approach for visualizing them in a way that meaningfully captured the evolutionary properties of sequences,” Vaishnav explains. “I really wanted to find a way to fill that gap, and contribute to the long-standing vision of creating a complete fitness landscape.”

      Martin Taylor, a professor of genetics at the University of Edinburgh’s Medical Research Council Human Genetics Unit who was not involved in the research, says the study shows that artificial intelligence can not only predict the effect of regulatory DNA changes, but also reveal the underlying principles that govern millions of years of evolution.

      Despite the fact that the model was trained on just a fraction of yeast regulatory DNA in a few growth conditions, he’s impressed that it’s capable of making such useful predictions about the evolution of gene regulation in mammals.

      “There are obvious near-term applications, such as the custom design of regulatory DNA for yeast in brewing, baking, and biotechnology,” he explains. “But extensions of this work could also help identify disease mutations in human regulatory DNA that are currently difficult to find and largely overlooked in the clinic. This work suggests there is a bright future for AI models of gene regulation trained on richer, more complex, and more diverse datasets.”

      Even before the study was formally published, Vaishnav began receiving queries from other researchers hoping to use the model to devise non-coding DNA sequences for use in gene therapies.

      “People have been studying regulatory evolution and fitness landscapes for decades now,” Vaishnav says. “I think our framework will go a long way in answering fundamental, open questions about the evolution and evolvability of gene regulatory DNA — and even help us design biological sequences for exciting new applications.” More

    • 63 Shares149 Views

      in Data Management & Statistics

      Injecting fairness into machine-learning models

      by

      If a machine-learning model is trained using an unbalanced dataset, such as one that contains far more images of people with lighter skin than people with darker skin, there is serious risk the model’s predictions will be unfair when it is deployed in the real world.

      But this is only one part of the problem. MIT researchers have found that machine-learning models that are popular for image recognition tasks actually encode bias when trained on unbalanced data. This bias within the model is impossible to fix later on, even with state-of-the-art fairness-boosting techniques, and even when retraining the model with a balanced dataset.      

      So, the researchers came up with a technique to introduce fairness directly into the model’s internal representation itself. This enables the model to produce fair outputs even if it is trained on unfair data, which is especially important because there are very few well-balanced datasets for machine learning.

      The solution they developed not only leads to models that make more balanced predictions, but also improves their performance on downstream tasks like facial recognition and animal species classification.

      “In machine learning, it is common to blame the data for bias in models. But we don’t always have balanced data. So, we need to come up with methods that actually fix the problem with imbalanced data,” says lead author Natalie Dullerud, a graduate student in the Healthy ML Group of the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT.

      Dullerud’s co-authors include Kimia Hamidieh, a graduate student in the Healthy ML Group; Karsten Roth, a former visiting researcher who is now a graduate student at the University of Tubingen; Nicolas Papernot, an assistant professor in the University of Toronto’s Department of Electrical Engineering and Computer Science; and senior author Marzyeh Ghassemi, an assistant professor and head of the Healthy ML Group. The research will be presented at the International Conference on Learning Representations.

      Defining fairness

      The machine-learning technique the researchers studied is known as deep metric learning, which is a broad form of representation learning. In deep metric learning, a neural network learns the similarity between objects by mapping similar photos close together and dissimilar photos far apart. During training, this neural network maps images in an “embedding space” where a similarity metric between photos corresponds to the distance between them.

      For example, if a deep metric learning model is being used to classify bird species, it will map photos of golden finches together in one part of the embedding space and cardinals together in another part of the embedding space. Once trained, the model can effectively measure the similarity of new images it hasn’t seen before. It would learn to cluster images of an unseen bird species close together, but farther from cardinals or golden finches within the embedding space.

      The similarity metrics the model learns are very robust, which is why deep metric learning is so often employed for facial recognition, Dullerud says. But she and her colleagues wondered how to determine if a similarity metric is biased.

      “We know that data reflect the biases of processes in society. This means we have to shift our focus to designing methods that are better suited to reality,” says Ghassemi.

      The researchers defined two ways that a similarity metric can be unfair. Using the example of facial recognition, the metric will be unfair if it is more likely to embed individuals with darker-skinned faces closer to each other, even if they are not the same person, than it would if those images were people with lighter-skinned faces. Second, it will be unfair if the features it learns for measuring similarity are better for the majority group than for the minority group.

      The researchers ran a number of experiments on models with unfair similarity metrics and were unable to overcome the bias the model had learned in its embedding space.

      “This is quite scary because it is a very common practice for companies to release these embedding models and then people finetune them for some downstream classification task. But no matter what you do downstream, you simply can’t fix the fairness problems that were induced in the embedding space,” Dullerud says.

      Even if a user retrains the model on a balanced dataset for the downstream task, which is the best-case scenario for fixing the fairness problem, there are still performance gaps of at least 20 percent, she says.

      The only way to solve this problem is to ensure the embedding space is fair to begin with.

      Learning separate metrics

      The researchers’ solution, called Partial Attribute Decorrelation (PARADE), involves training the model to learn a separate similarity metric for a sensitive attribute, like skin tone, and then decorrelating the skin tone similarity metric from the targeted similarity metric. If the model is learning the similarity metrics of different human faces, it will learn to map similar faces close together and dissimilar faces far apart using features other than skin tone.

      Any number of sensitive attributes can be decorrelated from the targeted similarity metric in this way. And because the similarity metric for the sensitive attribute is learned in a separate embedding space, it is discarded after training so only the targeted similarity metric remains in the model.

      Their method is applicable to many situations because the user can control the amount of decorrelation between similarity metrics. For instance, if the model will be diagnosing breast cancer from mammogram images, a clinician likely wants some information about biological sex to remain in the final embedding space because it is much more likely that women will have breast cancer than men, Dullerud explains.

      They tested their method on two tasks, facial recognition and classifying bird species, and found that it reduced performance gaps caused by bias, both in the embedding space and in the downstream task, regardless of the dataset they used.

      Moving forward, Dullerud is interested in studying how to force a deep metric learning model to learn good features in the first place.

      “How do you properly audit fairness? That is an open question right now. How can you tell that a model is going to be fair, or that it is only going to be fair in certain situations, and what are those situations? Those are questions I am really interested in moving forward,” she says. More

    • 125 Shares199 Views

      in Data Management & Statistics

      Using artificial intelligence to find anomalies hiding in massive datasets

      by

      Identifying a malfunction in the nation’s power grid can be like trying to find a needle in an enormous haystack. Hundreds of thousands of interrelated sensors spread across the U.S. capture data on electric current, voltage, and other critical information in real time, often taking multiple recordings per second.

      Researchers at the MIT-IBM Watson AI Lab have devised a computationally efficient method that can automatically pinpoint anomalies in those data streams in real time. They demonstrated that their artificial intelligence method, which learns to model the interconnectedness of the power grid, is much better at detecting these glitches than some other popular techniques.

      Because the machine-learning model they developed does not require annotated data on power grid anomalies for training, it would be easier to apply in real-world situations where high-quality, labeled datasets are often hard to come by. The model is also flexible and can be applied to other situations where a vast number of interconnected sensors collect and report data, like traffic monitoring systems. It could, for example, identify traffic bottlenecks or reveal how traffic jams cascade.

      “In the case of a power grid, people have tried to capture the data using statistics and then define detection rules with domain knowledge to say that, for example, if the voltage surges by a certain percentage, then the grid operator should be alerted. Such rule-based systems, even empowered by statistical data analysis, require a lot of labor and expertise. We show that we can automate this process and also learn patterns from the data using advanced machine-learning techniques,” says senior author Jie Chen, a research staff member and manager of the MIT-IBM Watson AI Lab.

      The co-author is Enyan Dai, an MIT-IBM Watson AI Lab intern and graduate student at the Pennsylvania State University. This research will be presented at the International Conference on Learning Representations.

      Probing probabilities

      The researchers began by defining an anomaly as an event that has a low probability of occurring, like a sudden spike in voltage. They treat the power grid data as a probability distribution, so if they can estimate the probability densities, they can identify the low-density values in the dataset. Those data points which are least likely to occur correspond to anomalies.

      Estimating those probabilities is no easy task, especially since each sample captures multiple time series, and each time series is a set of multidimensional data points recorded over time. Plus, the sensors that capture all that data are conditional on one another, meaning they are connected in a certain configuration and one sensor can sometimes impact others.

      To learn the complex conditional probability distribution of the data, the researchers used a special type of deep-learning model called a normalizing flow, which is particularly effective at estimating the probability density of a sample.

      They augmented that normalizing flow model using a type of graph, known as a Bayesian network, which can learn the complex, causal relationship structure between different sensors. This graph structure enables the researchers to see patterns in the data and estimate anomalies more accurately, Chen explains.

      “The sensors are interacting with each other, and they have causal relationships and depend on each other. So, we have to be able to inject this dependency information into the way that we compute the probabilities,” he says.

      This Bayesian network factorizes, or breaks down, the joint probability of the multiple time series data into less complex, conditional probabilities that are much easier to parameterize, learn, and evaluate. This allows the researchers to estimate the likelihood of observing certain sensor readings, and to identify those readings that have a low probability of occurring, meaning they are anomalies.

      Their method is especially powerful because this complex graph structure does not need to be defined in advance — the model can learn the graph on its own, in an unsupervised manner.

      A powerful technique

      They tested this framework by seeing how well it could identify anomalies in power grid data, traffic data, and water system data. The datasets they used for testing contained anomalies that had been identified by humans, so the researchers were able to compare the anomalies their model identified with real glitches in each system.

      Their model outperformed all the baselines by detecting a higher percentage of true anomalies in each dataset.

      “For the baselines, a lot of them don’t incorporate graph structure. That perfectly corroborates our hypothesis. Figuring out the dependency relationships between the different nodes in the graph is definitely helping us,” Chen says.

      Their methodology is also flexible. Armed with a large, unlabeled dataset, they can tune the model to make effective anomaly predictions in other situations, like traffic patterns.

      Once the model is deployed, it would continue to learn from a steady stream of new sensor data, adapting to possible drift of the data distribution and maintaining accuracy over time, says Chen.

      Though this particular project is close to its end, he looks forward to applying the lessons he learned to other areas of deep-learning research, particularly on graphs.

      Chen and his colleagues could use this approach to develop models that map other complex, conditional relationships. They also want to explore how they can efficiently learn these models when the graphs become enormous, perhaps with millions or billions of interconnected nodes. And rather than finding anomalies, they could also use this approach to improve the accuracy of forecasts based on datasets or streamline other classification techniques.

      This work was funded by the MIT-IBM Watson AI Lab and the U.S. Department of Energy. More

    • 75 Shares179 Views

      in Data Management & Statistics

      Deep-learning technique predicts clinical treatment outcomes

      by

      When it comes to treatment strategies for critically ill patients, clinicians want to be able to consider all their options and timing of administration, and make the optimal decision for their patients. While clinician experience and study has helped them to be successful in this effort, not all patients are the same, and treatment decisions at this crucial time could mean the difference between patient improvement and quick deterioration. Therefore, it would be helpful for doctors to be able to take a patient’s previous known health status and received treatments and use that to predict that patient’s health outcome under different treatment scenarios, in order to pick the best path.

      Now, a deep-learning technique, called G-Net, from researchers at MIT and IBM provides a window into causal counterfactual prediction, affording physicians the opportunity to explore how a patient might fare under different treatment plans. The foundation of G-Net is the g-computation algorithm, a causal inference method that estimates the effect of dynamic exposures in the presence of measured confounding variables — ones that may influence both treatments and outcomes. Unlike previous implementations of the g-computation framework, which have used linear modeling approaches, G-Net uses recurrent neural networks (RNN), which have node connections that allow them to better model temporal sequences with complex and nonlinear dynamics, like those found in the physiological and clinical time series data. In this way, physicians can develop alternative plans based on patient history and test them before making a decision.

      “Our ultimate goal is to develop a machine learning technique that would allow doctors to explore various ‘What if’ scenarios and treatment options,” says Li-wei Lehman, MIT research scientist in the MIT Institute for Medical Engineering and Science and an MIT-IBM Watson AI Lab project lead. “A lot of work has been done in terms of deep learning for counterfactual prediction but [it’s] been focusing on a point exposure setting,” or a static, time-varying treatment strategy, which doesn’t allow for adjustment of treatments as patient history changes. However, her team’s new prediction approach provides for treatment plan flexibility and chances for treatment alteration over time as patient covariate history and past treatments change. “G-Net is the first deep-learning approach based on g-computation that can predict both the population-level and individual-level treatment effects under dynamic and time varying treatment strategies.”

      The research, which was recently published in the Proceedings of Machine Learning Research, was co-authored by Rui Li MEng ’20, Stephanie Hu MEng ’21, former MIT postdoc Mingyu Lu MD, graduate student Yuria Utsumi, IBM research staff member Prithwish Chakraborty, IBM Research director of Hybrid Cloud Services Daby Sow, IBM data scientist Piyush Madan, IBM research scientist Mohamed Ghalwash, and IBM research scientist Zach Shahn.

      Tracking disease progression

      To build, validate, and test G-Net’s predictive abilities, the researchers considered the circulatory system in septic patients in the ICU. During critical care, doctors need to make trade-offs and judgement calls, such as ensuring the organs are receiving adequate blood supply without overworking the heart. For this, they could give intravenous fluids to patients to increase blood pressure; however, too much can cause edema. Alternatively, physicians can administer vasopressors, which act to contract blood vessels and raise blood pressure.

      In order to mimic this and demonstrate G-Net’s proof-of-concept, the team used CVSim, a mechanistic model of a human cardiovascular system that’s governed by 28 input variables characterizing the system’s current state, such as arterial pressure, central venous pressure, total blood volume, and total peripheral resistance, and modified it to simulate various disease processes (e.g., sepsis or blood loss) and effects of interventions (e.g., fluids and vasopressors). The researchers used CVSim to generate observational patient data for training and for “ground truth” comparison against counterfactual prediction. In their G-Net architecture, the researchers ran two RNNs to handle and predict variables that are continuous, meaning they can take on a range of values, like blood pressure, and categorical variables, which have discrete values, like the presence or absence of pulmonary edema. The researchers simulated the health trajectories of thousands of “patients” exhibiting symptoms under one treatment regime, let’s say A, for 66 timesteps, and used them to train and validate their model.

      Testing G-Net’s prediction capability, the team generated two counterfactual datasets. Each contained roughly 1,000 known patient health trajectories, which were created from CVSim using the same “patient” condition as the starting point under treatment A. Then at timestep 33, treatment changed to plan B or C, depending on the dataset. The team then performed 100 prediction trajectories for each of these 1,000 patients, whose treatment and medical history was known up until timestep 33 when a new treatment was administered. In these cases, the prediction agreed well with the “ground-truth” observations for individual patients and averaged population-level trajectories.

      A cut above the rest

      Since the g-computation framework is flexible, the researchers wanted to examine G-Net’s prediction using different nonlinear models — in this case, long short-term memory (LSTM) models, which are a type of RNN that can learn from previous data patterns or sequences — against the more classical linear models and a multilayer perception model (MLP), a type of neural network that can make predictions using a nonlinear approach. Following a similar setup as before, the team found that the error between the known and predicted cases was smallest in the LSTM models compared to the others. Since G-Net is able to model the temporal patterns of the patient’s ICU history and past treatment, whereas a linear model and MLP cannot, it was better able to predict the patient’s outcome.

      The team also compared G-Net’s prediction in a static, time-varying treatment setting against two state-of-the-art deep-learning based counterfactual prediction approaches, a recurrent marginal structural network (rMSN) and a counterfactual recurrent neural network (CRN), as well as a linear model and an MLP. For this, they investigated a model for tumor growth under no treatment, radiation, chemotherapy, and both radiation and chemotherapy scenarios. “Imagine a scenario where there’s a patient with cancer, and an example of a static regime would be if you only give a fixed dosage of chemotherapy, radiation, or any kind of drug, and wait until the end of your trajectory,” comments Lu. For these investigations, the researchers generated simulated observational data using tumor volume as the primary influence dictating treatment plans and demonstrated that G-Net outperformed the other models. One potential reason could be because g-computation is known to be more statistically efficient than rMSN and CRN, when models are correctly specified.

      While G-Net has done well with simulated data, more needs to be done before it can be applied to real patients. Since neural networks can be thought of as “black boxes” for prediction results, the researchers are beginning to investigate the uncertainty in the model to help ensure safety. In contrast to these approaches that recommend an “optimal” treatment plan without any clinician involvement, “as a decision support tool, I believe that G-Net would be more interpretable, since the clinicians would input treatment strategies themselves,” says Lehman, and “G-Net will allow them to be able to explore different hypotheses.” Further, the team has moved on to using real data from ICU patients with sepsis, bringing it one step closer to implementation in hospitals.

      “I think it is pretty important and exciting for real-world applications,” says Hu. “It’d be helpful to have some way to predict whether or not a treatment might work or what the effects might be — a quicker iteration process for developing these hypotheses for what to try, before actually trying to implement them in in a years-long, potentially very involved and very invasive type of clinical trial.”

      This research was funded by the MIT-IBM Watson AI Lab. More