Counterfactual instances offer human-interpretable insight into the local behaviour of machine learning models. We propose a general framework to generate sparse, in-distribution counterfactual model explanations which match a desired target prediction with a conditional generative model, allowing batches of counterfactual instances to be generated with a single forward pass. The method is flexible with respect to the type of generative model used as well as the task of the underlying predictive model. This allows straightforward application of the framework to different modalities such as images, time series or tabular data as well as generative model paradigms such as GANs or autoencoders and predictive tasks like classification or regression. We illustrate the effectiveness of our method on image (CelebA), time series (ECG) and mixed-type tabular (Adult Census) data.

Complex black-box machine learning models are regularly used in critical decision-making domains. This has given rise to several calls for algorithmic explainability. Many explanation algorithms proposed in literature assign importance to each feature individually. However, such explanations fail to capture the joint effects of sets of features. Indeed, few works so far formally analyze \coloremph{high dimensional model explanations}. In this paper, we propose a novel high dimension model explanation method that captures the joint effect of feature subsets. We propose a new axiomatization for a generalization of the Banzhaf index; our method can also be thought of as an approximation of a black-box model by a higher-order polynomial. In other words, this work justifies the use of the generalized Banzhaf index as a model explanation by showing that it uniquely satisfies a set of natural desiderata and that it is the optimal local approximation of a black-box model. Our empirical evaluation of our measure highlights how it manages to capture desirable behavior, whereas other measures that do not satisfy our axioms behave in an unpredictable manner.

In this era of explainable and interpretable Machine Learning, one merely cannot be content with simply training the model and obtaining predictions from it. To be able to really make an impact and obtain good results, we should also be able to probe and investigate our models. Apart from that, algorithmic fairness constraints and bias should also be clearly kept in mind before going ahead with the model. Investigating a model requires asking a lot of questions and one needs to have an acumen of a detective to probe and look for issues and inconsistencies within the models. Also, such a task is usually complex requiring to write a lot of custom code.

A key challenge in developing and deploying Machine Learning (ML) systems is understanding their performance across a wide range of inputs. To address this challenge, we created the What-If Tool, an open-source application that allows practitioners to probe, visualize, and analyze ML systems, with minimal coding. The What-If Tool lets practitioners test performance in hypothetical situations, analyze the importance of different data features, and visualize model behavior across multiple models and subsets of input data. It also lets practitioners measure systems according to multiple ML fairness metrics. We describe the design of the tool, and report on real-life usage at different organizations.

On December 15, 2017, the United Nations Special Rapporteur on extreme poverty and human rights, Philip Alston, issued a damning report on his visit to the United States. He cited data from the Stanford Center on Inequality and Poverty, which reports that "in terms of labor markets, poverty, safety net, wealth inequality, and economic mobility, the US comes in last of the top 10 most well-off countries, and 18th amongst the top 21." Alston wrote that "the American Dream is rapidly becoming the American Illusion, as the US now has the lowest rate of social mobility of any of the rich countries." Just a few days before, on December 11, The Boston Globe's Spotlight team ran a story showing that the median net worth of nonimmigrant African American households in the Boston area is $8, in contrast to the $247,500 net worth for white households in the Boston area. Clearly income disparity is ripping the nation apart, and none of the efforts or programs seeking to address it seems to be working. I myself have been, for the past couple of years, engaged in a broad discussion about the future of work with some thoughtful tech leaders and representatives of the Catholic Church who have similar concerns, and the notion of a universal basic income (UBI) keeps coming up.

Algorithmic systems that employ machine learning play an increasing role in making substantive decisions in modern society, ranging from online personalization to insurance and credit decisions to predictive policing. But their decision-making processes are often opaque--it is difficult to explain why a certain decision was made. We develop a formal foundation to improve the transparency of such decision-making systems. Specifically, we introduce a family of Quantitative Input Influence (QII) measures that capture the degree of influence of inputs on outputs of systems. These measures provide a foundation for the design of transparency reports that accompany system decisions (e.g., explaining a specific credit decision) and for testing tools useful for internal and external oversight (e.g., to detect algorithmic discrimination). Distinctively, our causal QII measures carefully account for correlated inputs while measuring influence. They support a general class of transparency queries and can, in particular, explain decisions about individuals (e.g., a loan decision) and groups (e.g., disparate impact based on gender). Finally, since single inputs may not always have high influence, the QII measures also quantify the joint influence of a set of inputs (e.g., age and income) on outcomes (e.g.