The large size and complex decision mechanisms of state-of-the-art text classifiers make it difficult for humans to understand their predictions, leading to a potential lack of trust by the users. These issues have led to the adoption of methods like SHAP and Integrated Gradients to explain classification decisions by assigning importance scores to input tokens. However, prior work, using different randomization tests, has shown that interpretations generated by these methods may not be robust. For instance, models making the same predictions on the test set may still lead to different feature importance rankings. In order to address the lack of robustness of token-based interpretability, we explore explanations at higher semantic levels like sentences. We use computational metrics and human subject studies to compare the quality of sentence-based interpretations against token-based ones. Our experiments show that higher-level feature attributions offer several advantages: 1) they are more robust as measured by the randomization tests, 2) they lead to lower variability when using approximation-based methods like SHAP, and 3) they are more intelligible to humans in situations where the linguistic coherence resides at a higher granularity level. Based on these findings, we show that token-based interpretability, while being a convenient first choice given the input interfaces of the ML models, is not the most effective one in all situations.
With the increasing adoption of machine learning (ML) models and systems in high-stakes settings across different industries, guaranteeing a model's performance after deployment has become crucial. Monitoring models in production is a critical aspect of ensuring their continued performance and reliability. We present Amazon SageMaker Model Monitor, a fully managed service that continuously monitors the quality of machine learning models hosted on Amazon SageMaker. Our system automatically detects data, concept, bias, and feature attribution drift in models in real-time and provides alerts so that model owners can take corrective actions and thereby maintain high quality models. We describe the key requirements obtained from customers, system design and architecture, and methodology for detecting different types of drift. Further, we provide quantitative evaluations followed by use cases, insights, and lessons learned from more than 1.5 years of production deployment.
Understanding the predictions made by machine learning (ML) models and their potential biases remains a challenging and labor-intensive task that depends on the application, the dataset, and the specific model. We present Amazon SageMaker Clarify, an explainability feature for Amazon SageMaker that launched in December 2020, providing insights into data and ML models by identifying biases and explaining predictions. It is deeply integrated into Amazon SageMaker, a fully managed service that enables data scientists and developers to build, train, and deploy ML models at any scale. Clarify supports bias detection and feature importance computation across the ML lifecycle, during data preparation, model evaluation, and post-deployment monitoring. We outline the desiderata derived from customer input, the modular architecture, and the methodology for bias and explanation computations. Further, we describe the technical challenges encountered and the tradeoffs we had to make. For illustration, we discuss two customer use cases. We present our deployment results including qualitative customer feedback and a quantitative evaluation. Finally, we summarize lessons learned, and discuss best practices for the successful adoption of fairness and explanation tools in practice.
We study the problem of training a model that must obey demographic fairness conditions when the sensitive features are not available at training time -- in other words, how can we train a model to be fair by race when we don't have data about race? We adopt a fairness pipeline perspective, in which an "upstream" learner that does have access to the sensitive features will learn a proxy model for these features from the other attributes. The goal of the proxy is to allow a general "downstream" learner -- with minimal assumptions on their prediction task -- to be able to use the proxy to train a model that is fair with respect to the true sensitive features. We show that obeying multiaccuracy constraints with respect to the downstream model class suffices for this purpose, and provide sample- and oracle efficient-algorithms and generalization bounds for learning such proxies. In general, multiaccuracy can be much easier to satisfy than classification accuracy, and can be satisfied even when the sensitive features are hard to predict.
With the ever-increasing complexity of neural language models, practitioners have turned to methods for understanding the predictions of these models. One of the most well-adopted approaches for model interpretability is feature-based interpretability, i.e., ranking the features in terms of their impact on model predictions. Several prior studies have focused on assessing the fidelity of feature-based interpretability methods, i.e., measuring the impact of dropping the top-ranked features on the model output. However, relatively little work has been conducted on quantifying the robustness of interpretations. In this work, we assess the robustness of interpretations of neural text classifiers, specifically, those based on pretrained Transformer encoders, using two randomization tests. The first compares the interpretations of two models that are identical except for their initializations. The second measures whether the interpretations differ between a model with trained parameters and a model with random parameters. Both tests show surprising deviations from expected behavior, raising questions about the extent of insights that practitioners may draw from interpretations.
The interaction patterns of employees in social and professional networks play an important role in the success of employees and organizations as a whole. However, in many fields there is a severe under-representation of minority groups; moreover, minority individuals may be segregated from the rest of the network or isolated from one another. While the problem of increasing the representation of minority groups in various fields has been well-studied, diver- sification in terms of numbers alone may not be sufficient: social relationships should also be considered. In this work, we consider the problem of assigning a set of employment candidates to positions in a social network so that diversity and overall fitness are maximized, and propose Fair Employee Assignment (FairEA), a novel algorithm for finding such a matching. The output from FairEA can be used as a benchmark by organizations wishing to evaluate their hiring and assignment practices. On real and synthetic networks, we demonstrate that FairEA does well at finding high-fitness, high-diversity matchings.
We initiate the study of fairness for ordinal regression, or ordinal classification. We adapt two fairness notions previously considered in fair ranking and propose a strategy for training a predictor that is approximately fair according to either notion. Our predictor consists of a threshold model, composed of a scoring function and a set of thresholds, and our strategy is based on a reduction to fair binary classification for learning the scoring function and local search for choosing the thresholds. We can control the extent to which we care about the accuracy vs the fairness of the predictor via a parameter. In extensive experiments we show that our strategy allows us to effectively explore the accuracy-vs-fairness trade-off and that it often compares favorably to "unfair" state-of-the-art methods for ordinal regression in that it yields predictors that are only slightly less accurate, but significantly more fair.
We propose, implement, and evaluate a new algorithm for releasing answers to very large numbers of statistical queries like $k$-way marginals, subject to differential privacy. Our algorithm makes adaptive use of a continuous relaxation of the Projection Mechanism, which answers queries on the private dataset using simple perturbation, and then attempts to find the synthetic dataset that most closely matches the noisy answers. We use a continuous relaxation of the synthetic dataset domain which makes the projection loss differentiable, and allows us to use efficient ML optimization techniques and tooling. Rather than answering all queries up front, we make judicious use of our privacy budget by iteratively and adaptively finding queries for which our (relaxed) synthetic data has high error, and then repeating the projection. We perform extensive experimental evaluations across a range of parameters and datasets, and find that our method outperforms existing algorithms in many cases, especially when the privacy budget is small or the query class is large.
Machine learning models are often implemented in cohort with humans in the pipeline, with the model having an option to defer to a domain expert in cases where it has low confidence in its inference. Our goal is to design mechanisms for ensuring accuracy and fairness in such prediction systems that combine machine learning model inferences and domain expert predictions. Prior work on "deferral systems" in classification settings has focused on the setting of a pipeline with a single expert and aimed to accommodate the inaccuracies and biases of this expert to simultaneously learn an inference model and a deferral system. Our work extends this framework to settings where multiple experts are available, with each expert having their own domain of expertise and biases. We propose a framework that simultaneously learns a classifier and a deferral system, with the deferral system choosing to defer to one or more human experts in cases of input where the classifier has low confidence. We test our framework on a synthetic dataset and a content moderation dataset with biased synthetic experts, and show that it significantly improves the accuracy and fairness of the final predictions, compared to the baselines. We also collect crowdsourced labels for the content moderation task to construct a real-world dataset for the evaluation of hybrid machine-human frameworks and show that our proposed learning framework outperforms baselines on this real-world dataset as well.