Federated learning (FL) is a machine learning setting where many clients (e.g. mobile devices or whole organizations) collaboratively train a model under the orchestration of a central server (e.g. service provider), while keeping the training data decentralized. FL embodies the principles of focused data collection and minimization, and can mitigate many of the systemic privacy risks and costs resulting from traditional, centralized machine learning and data science approaches. Motivated by the explosive growth in FL research, this paper discusses recent advances and presents an extensive collection of open problems and challenges.

Advances and Open Problems in Federated Learning

Deep learning has triggered the current rise of artificial intelligence and is the workhorse of today’s machine intelligence. Numerous success stories have rapidly spread all over science, industry and society, but its limitations have only recently come into focus. In this Perspective we seek to distil how many of deep learning’s failures can be seen as different symptoms of the same underlying problem: shortcut learning. Shortcuts are decision rules that perform well on standard benchmarks but fail to transfer to more challenging testing conditions, such as real-world scenarios. Related issues are known in comparative psychology, education and linguistics, suggesting that shortcut learning may be a common characteristic of learning systems, biological and artificial alike. Based on these observations, we develop a set of recommendations for model interpretation and benchmarking, highlighting recent advances in machine learning to improve robustness and transferability from the lab to real-world applications. Deep learning has resulted in impressive achievements, but under what circumstances does it fail, and why? The authors propose that its failures are a consequence of shortcut learning, a common characteristic across biological and artificial systems in which strategies that appear to have solved a problem fail unexpectedly under different circumstances.

Shortcut learning in deep neural networks

The nascent field of fair machine learning aims to ensure that decisions guided by algorithms are equitable. Over the last several years, three formal definitions of fairness have gained prominence: (1) anti-classification, meaning that protected attributes---like race, gender, and their proxies---are not explicitly used to make decisions; (2) classification parity, meaning that common measures of predictive performance (e.g., false positive and false negative rates) are equal across groups defined by the protected attributes; and (3) calibration, meaning that conditional on risk estimates, outcomes are independent of protected attributes. Here we show that all three of these fairness definitions suffer from significant statistical limitations. Requiring anti-classification or classification parity can, perversely, harm the very groups they were designed to protect; and calibration, though generally desirable, provides little guarantee that decisions are equitable. In contrast to these formal fairness criteria, we argue that it is often preferable to treat similarly risky people similarly, based on the most statistically accurate estimates of risk that one can produce. Such a strategy, while not universally applicable, often aligns well with policy objectives; notably, this strategy will typically violate both anti-classification and classification parity. In practice, it requires significant effort to construct suitable risk estimates. One must carefully define and measure the targets of prediction to avoid retrenching biases in the data. But, importantly, one cannot generally address these difficulties by requiring that algorithms satisfy popular mathematical formalizations of fairness. By highlighting these challenges in the foundation of fair machine learning, we hope to help researchers and practitioners productively advance the area.

The Measure and Mismeasure of Fairness: A Critical Review of Fair Machine Learning.

Distribution shifts -- where the training distribution differs from the test distribution -- can substantially degrade the accuracy of machine learning (ML) systems deployed in the wild. Despite their ubiquity, these real-world distribution shifts are under-represented in the datasets widely used in the ML community today. To address this gap, we present WILDS, a curated collection of 8 benchmark datasets that reflect a diverse range of distribution shifts which naturally arise in real-world applications, such as shifts across hospitals for tumor identification; across camera traps for wildlife monitoring; and across time and location in satellite imaging and poverty mapping. On each dataset, we show that standard training results in substantially lower out-of-distribution than in-distribution performance, and that this gap remains even with models trained by existing methods for handling distribution shifts. This underscores the need for new training methods that produce models which are more robust to the types of distribution shifts that arise in practice. To facilitate method development, we provide an open-source package that automates dataset loading, contains default model architectures and hyperparameters, and standardizes evaluations. Code and leaderboards are available at this https URL.

WILDS: A Benchmark of in-the-Wild Distribution Shifts

Overparameterized neural networks can be highly accurate on average on an i.i.d. test set yet consistently fail on atypical groups of the data (e.g., by learning spurious correlations that hold on average but not in such groups). Distributionally robust optimization (DRO) allows us to learn models that instead minimize the worst-case training loss over a set of pre-defined groups. However, we find that naively applying group DRO to overparameterized neural networks fails: these models can perfectly fit the training data, and any model with vanishing average training loss also already has vanishing worst-case training loss. Instead, the poor worst-case performance arises from poor generalization on some groups. By coupling group DRO models with increased regularization---a stronger-than-typical L2 penalty or early stopping---we achieve substantially higher worst-group accuracies, with 10-40 percentage point improvements on a natural language inference task and two image tasks, while maintaining high average accuracies. Our results suggest that regularization is important for worst-group generalization in the overparameterized regime, even if it is not needed for average generalization. Finally, we introduce a stochastic optimization algorithm, with convergence guarantees, to efficiently train group DRO models.

Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization.

Machine learning models (e.g., speech recognizers) are usually trained to minimize average loss, which results in representation disparity---minority groups (e.g., non-native speakers) contribute less to the training objective and thus tend to suffer higher loss. Worse, as model accuracy affects user retention, a minority group can shrink over time. In this paper, we first show that the status quo of empirical risk minimization (ERM) amplifies representation disparity over time, which can even make initially fair models unfair. To mitigate this, we develop an approach based on distributionally robust optimization (DRO), which minimizes the worst case risk over all distributions close to the empirical distribution. We prove that this approach controls the risk of the minority group at each time step, in the spirit of Rawlsian distributive justice, while remaining oblivious to the identity of the groups. We demonstrate that DRO prevents disparity amplification on examples where ERM fails, and show improvements in minority group user satisfaction in a real-world text autocomplete task.

/pdf/fairness-without-demographics-in-repeated-loss-minimization-l1ugmz1mlq.pdf

Fairness Without Demographics in Repeated Loss Minimization

Fairness for Machine Learning has received considerable attention, recently. Various mathematical formulations of fairness have been proposed, and it has been shown that it is impossible to satisfy all of them simultaneously. The literature so far has dealt with these impossibility results by quantifying the tradeoffs between different formulations of fairness. Our work takes a different perspective on this issue. Rather than requiring all notions of fairness to (partially) hold at the same time, we ask which one of them is the most appropriate given the societal domain in which the decision-making model is to be deployed. We take a descriptive approach and set out to identify the notion of fairness that best captures lay people's perception of fairness. We run adaptive experiments designed to pinpoint the most compatible notion of fairness with each participant's choices through a small number of tests. Perhaps surprisingly, we find that the most simplistic mathematical definition of fairness---namely, demographic parity---most closely matches people's idea of fairness in two distinct application scenarios. This conclusion remains intact even when we explicitly tell the participants about the alternative, more complicated definitions of fairness, and we reduce the cognitive burden of evaluating those notions for them. Our findings have important implications for the Fair ML literature and the discourse on formalizing algorithmic fairness.

https://dl.acm.org/doi/pdf/10.1145/3292500.3330664

Mathematical Notions vs. Human Perception of Fairness: A Descriptive Approach to Fairness for Machine Learning

Fairness for Machine Learning has received considerable attention, recently. Various mathematical formulations of fairness have been proposed, and it has been shown that it is impossible to satisfy all of them simultaneously. The literature so far has dealt with these impossibility results by quantifying the tradeoffs between different formulations of fairness. Our work takes a different perspective on this issue. Rather than requiring all notions of fairness to (partially) hold at the same time, we ask which one of them is the most appropriate given the societal domain in which the decision-making model is to be deployed. We take a descriptive approach and set out to identify the notion of fairness that best captures \emph{lay people's perception of fairness}. We run adaptive experiments designed to pinpoint the most compatible notion of fairness with each participant's choices through a small number of tests. Perhaps surprisingly, we find that the most simplistic mathematical definition of fairness---namely, demographic parity---most closely matches people's idea of fairness in two distinct application scenarios. This conclusion remains intact even when we explicitly tell the participants about the alternative, more complicated definitions of fairness, and we reduce the cognitive burden of evaluating those notions for them. Our findings have important implications for the Fair ML literature and the discourse on formalizing algorithmic fairness.

The reliability of machine learning systems critically assumes that the associations between features and labels remain similar between training and test distributions. However, unmeasured variables, such as confounders, break this assumption---useful correlations between features and labels at training time can become useless or even harmful at test time. For example, high obesity is generally predictive for heart disease, but this relation may not hold for smokers who generally have lower rates of obesity and higher rates of heart disease. We present a framework for making models robust to spurious correlations by leveraging humans' common sense knowledge of causality. Specifically, we use human annotation to augment each training example with a potential unmeasured variable (i.e. an underweight patient with heart disease may be a smoker), reducing the problem to a covariate shift problem. We then introduce a new distributionally robust optimization objective over unmeasured variables (UV-DRO) to control the worst-case loss over possible test-time shifts. Empirically, we show improvements of 5-10% on a digit recognition task confounded by rotation, and 1.5-5% on the task of analyzing NYPD Police Stops confounded by location.

Megha Srivastava

Papers

Fairness Without Demographics in Repeated Loss Minimization

Mathematical Notions vs. Human Perception of Fairness: A Descriptive Approach to Fairness for Machine Learning

Fairness Without Demographics in Repeated Loss Minimization

Mathematical Notions vs. Human Perception of Fairness: A Descriptive Approach to Fairness for Machine Learning

Robustness to Spurious Correlations via Human Annotations