Predictive models are increasingly used to make various consequential decisions in high-stakes domains such as healthcare, finance, and policy. It becomes critical to ensure that these models make accurate predictions, are robust to shifts in the data, do not rely on spurious features, and do not unduly discriminate against minority groups. To this end, several approaches spanning various areas such as explainability, fairness, and robustness have been proposed in recent literature. Such approaches need to be human-centered as they cater to the understanding of the models to their users. However, there is a research gap in understanding the human-centric needs and challenges of monitoring machine learning (ML) models once they are deployed. To fill this gap, we conducted an interview study with 13 practitioners who have experience at the intersection of deploying ML models and engaging with customers spanning domains such as financial services, healthcare, hiring, online retail, computational advertising, and conversational assistants. We identified various human-centric challenges and requirements for model monitoring in real-world applications. Specifically, we found the need and the challenge for the model monitoring systems to clarify the impact of the monitoring observations on outcomes. Further, such insights must be actionable, robust, customizable for domain-specific use cases, and cognitively considerate to avoid information overload.
Despite the plethora of post hoc model explanation methods, the basic properties and behavior of these methods and the conditions under which each one is effective are not well understood. In this work, we bridge these gaps and address a fundamental question: Which explanation method should one use in a given situation? To this end, we adopt a function approximation perspective and formalize the local function approximation (LFA) framework. We show that popular explanation methods are instances of this framework, performing function approximations of the underlying model in different neighborhoods using different loss functions. We introduce a no free lunch theorem for explanation methods which demonstrates that no single method can perform optimally across all neighbourhoods and calls for choosing among methods. To choose among methods, we set forth a guiding principle based on the function approximation perspective, considering a method to be effective if it recovers the underlying model when the model is a member of the explanation function class. Then, we analyze the conditions under which popular explanation methods are effective and provide recommendations for choosing among explanation methods and creating new ones. Lastly, we empirically validate our theoretical results using various real world datasets, model classes, and prediction tasks. By providing a principled mathematical framework which unifies diverse explanation methods, our work characterizes the behaviour of these methods and their relation to one another, guides the choice of explanation methods, and paves the way for the creation of new ones.
As post hoc explanation methods are increasingly being leveraged to explain complex models in high-stakes settings, it becomes critical to ensure that the quality of the resulting explanations is consistently high across various population subgroups including the minority groups. For instance, it should not be the case that explanations associated with instances belonging to a particular gender subgroup (e.g., female) are less accurate than those associated with other genders. However, there is little to no research that assesses if there exist such group-based disparities in the quality of the explanations output by state-of-the-art explanation methods. In this work, we address the aforementioned gaps by initiating the study of identifying group-based disparities in explanation quality. To this end, we first outline the key properties which constitute explanation quality and where disparities can be particularly problematic. We then leverage these properties to propose a novel evaluation framework which can quantitatively measure disparities in the quality of explanations output by state-of-the-art methods. Using this framework, we carry out a rigorous empirical analysis to understand if and when group-based disparities in explanation quality arise. Our results indicate that such disparities are more likely to occur when the models being explained are complex and highly non-linear. In addition, we also observe that certain post hoc explanation methods (e.g., Integrated Gradients, SHAP) are more likely to exhibit the aforementioned disparities. To the best of our knowledge, this work is the first to highlight and study the problem of group-based disparities in explanation quality. In doing so, our work sheds light on previously unexplored ways in which explanation methods may introduce unfairness in real world decision making.
As attribution-based explanation methods are increasingly used to establish model trustworthiness in high-stakes situations, it is critical to ensure that these explanations are stable, e.g., robust to infinitesimal perturbations to an input. However, previous works have shown that state-of-the-art explanation methods generate unstable explanations. Here, we introduce metrics to quantify the stability of an explanation and show that several popular explanation methods are unstable. In particular, we propose new Relative Stability metrics that measure the change in output explanation with respect to change in input, model representation, or output of the underlying predictor. Finally, our experimental evaluation with three real-world datasets demonstrates interesting insights for seven explanation methods and different stability metrics.
As machine learning (ML) models are increasingly being deployed in high-stakes applications, there has been growing interest in providing recourse to individuals adversely impacted by model predictions (e.g., an applicant whose loan has been denied). To this end, several post hoc techniques have been proposed in recent literature. These techniques generate recourses under the assumption that the affected individuals will implement the prescribed recourses exactly. However, recent studies suggest that individuals often implement recourses in a noisy and inconsistent manner - e.g., raising their salary by \$505 if the prescribed recourse suggested an increase of \$500. Motivated by this, we introduce and study the problem of recourse invalidation in the face of noisy human responses. More specifically, we theoretically and empirically analyze the behavior of state-of-the-art algorithms, and demonstrate that the recourses generated by these algorithms are very likely to be invalidated if small changes are made to them. We further propose a novel framework, EXPECTing noisy responses (EXPECT), which addresses the aforementioned problem by explicitly minimizing the probability of recourse invalidation in the face of noisy responses. Experimental evaluation with multiple real world datasets demonstrates the efficacy of the proposed framework, and supports our theoretical findings
As various post hoc explanation methods are increasingly being leveraged to explain complex models in high-stakes settings, it becomes critical to develop a deeper understanding of if and when the explanations output by these methods disagree with each other, and how such disagreements are resolved in practice. However, there is little to no research that provides answers to these critical questions. In this work, we introduce and study the disagreement problem in explainable machine learning. More specifically, we formalize the notion of disagreement between explanations, analyze how often such disagreements occur in practice, and how do practitioners resolve these disagreements. To this end, we first conduct interviews with data scientists to understand what constitutes disagreement between explanations generated by different methods for the same model prediction, and introduce a novel quantitative framework to formalize this understanding. We then leverage this framework to carry out a rigorous empirical analysis with four real-world datasets, six state-of-the-art post hoc explanation methods, and eight different predictive models, to measure the extent of disagreement between the explanations generated by various popular explanation methods. In addition, we carry out an online user study with data scientists to understand how they resolve the aforementioned disagreements. Our results indicate that state-of-the-art explanation methods often disagree in terms of the explanations they output. Our findings also underscore the importance of developing principled evaluation metrics that enable practitioners to effectively compare explanations.
As practitioners increasingly deploy machine learning models in critical domains such as health care, finance, and policy, it becomes vital to ensure that domain experts function effectively alongside these models. Explainability is one way to bridge the gap between human decision-makers and machine learning models. However, most of the existing work on explainability focuses on one-off, static explanations like feature importances or rule lists. These sorts of explanations may not be sufficient for many use cases that require dynamic, continuous discovery from stakeholders. In the literature, few works ask decision-makers about the utility of existing explanations and other desiderata they would like to see in an explanation going forward. In this work, we address this gap and carry out a study where we interview doctors, healthcare professionals, and policymakers about their needs and desires for explanations. Our study indicates that decision-makers would strongly prefer interactive explanations in the form of natural language dialogues. Domain experts wish to treat machine learning models as "another colleague", i.e., one who can be held accountable by asking why they made a particular decision through expressive and accessible natural language interactions. Considering these needs, we outline a set of five principles researchers should follow when designing interactive explanations as a starting place for future work. Further, we show why natural language dialogues satisfy these principles and are a desirable way to build interactive explanations. Next, we provide a design of a dialogue system for explainability and discuss the risks, trade-offs, and research opportunities of building these systems. Overall, we hope our work serves as a starting place for researchers and engineers to design interactive explainability systems.
As machine learning models are increasingly used in critical decision-making settings (e.g., healthcare, finance), there has been a growing emphasis on developing methods to explain model predictions. Such \textit{explanations} are used to understand and establish trust in models and are vital components in machine learning pipelines. Though explanations are a critical piece in these systems, there is little understanding about how they are vulnerable to manipulation by adversaries. In this paper, we discuss how two broad classes of explanations are vulnerable to manipulation. We demonstrate how adversaries can design biased models that manipulate model agnostic feature attribution methods (e.g., LIME \& SHAP) and counterfactual explanations that hill-climb during the counterfactual search (e.g., Wachter's Algorithm \& DiCE) into \textit{concealing} the model's biases. These vulnerabilities allow an adversary to deploy a biased model, yet explanations will not reveal this bias, thereby deceiving stakeholders into trusting the model. We evaluate the manipulations on real world data sets, including COMPAS and Communities \& Crime, and find explanations can be manipulated in practice.
In situations where explanations of black-box models may be useful, the fairness of the black-box is also often a relevant concern. However, the link between the fairness of the black-box model and the behavior of explanations for the black-box is unclear. We focus on explanations applied to tabular datasets, suggesting that explanations do not necessarily preserve the fairness properties of the black-box algorithm. In other words, explanation algorithms can ignore or obscure critical relevant properties, creating incorrect or misleading explanations. More broadly, we propose future research directions for evaluating and generating explanations such that they are informative and relevant from a fairness perspective.
Counterfactual explanations and adversarial examples have emerged as critical research areas for addressing the explainability and robustness goals of machine learning (ML). While counterfactual explanations were developed with the goal of providing recourse to individuals adversely impacted by algorithmic decisions, adversarial examples were designed to expose the vulnerabilities of ML models. While prior research has hinted at the commonalities between these frameworks, there has been little to no work on systematically exploring the connections between the literature on counterfactual explanations and adversarial examples. In this work, we make one of the first attempts at formalizing the connections between counterfactual explanations and adversarial examples. More specifically, we theoretically analyze salient counterfactual explanation and adversarial example generation methods, and highlight the conditions under which they behave similarly. Our analysis demonstrates that several popular counterfactual explanation and adversarial example generation methods such as the ones proposed by Wachter et. al. and Carlini and Wagner (with mean squared error loss), and C-CHVAE and natural adversarial examples by Zhao et. al. are equivalent. We also bound the distance between counterfactual explanations and adversarial examples generated by Wachter et. al. and DeepFool methods for linear models. Finally, we empirically validate our theoretical findings using extensive experimentation with synthetic and real world datasets.