Machine learning based decision making systems are increasingly affecting humans. An individual can suffer an undesirable outcome under such decision making systems (e.g. denied credit) irrespective of whether the decision is fair or accurate. Individual recourse pertains to the problem of providing an actionable set of changes a person can undertake in order to improve their outcome. We propose a recourse algorithm that models the underlying data distribution or manifold. We then provide a mechanism to generate the smallest set of changes that will improve an individual's outcome. This mechanism can be easily used to provide recourse for any differentiable machine learning based decision making system. Further, the resulting algorithm is shown to be applicable to both supervised classification and causal decision making systems. Our work attempts to fill gaps in existing fairness literature that have primarily focused on discovering and/or algorithmically enforcing fairness constraints on decision making systems. This work also provides an alternative approach to generating counterfactual explanations.
UC San Diego（加州大学圣地亚哥分校）；Maternity Foundation（产妇基金会）
Mobile health apps provide a unique means of collecting data that can be used to deliver adaptive interventions.The predicted outcomes considerably influence the selection of such interventions. Recourse via counterfactuals provides tangible mechanisms to modify user predictions. By identifying plausible actions that increase the likelihood of a desired prediction, stakeholders are afforded agency over their predictions. Furthermore, recourse mechanisms enable counterfactual reasoning that can help provide insights into candidates for causal interventional features. We demonstrate the feasibil…
Harvard University（哈佛大学）；Allen Institute for Artificial Intelligence（艾伦人工智能研究所）；University of Pennsylvania（宾夕法尼亚大学）
As machine learning models are increasingly deployed in high-stakes domains such as legal and financial decision-making, there has been growing interest in post-hoc methods for generating counterfactual explanations. Such explanations provide individuals adversely impacted by predicted outcomes (e.g., an applicant denied a loan) with recourse -- i.e., a description of how they can change their features to obtain a positive outcome. We propose a novel algorithm that leverages adversarial training and PAC confidence sets to learn models that theoretically guarantee recourse to affected individua…
University of Tübingen（图宾根大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；ETH Zürich（苏黎世联邦理工学院）
Algorithmic recourse seeks to provide actionable recommendations for individuals to overcome unfavorable classification outcomes from automated decision-making systems. Recourse recommendations should ideally be robust to reasonably small uncertainty in the features of the individual seeking recourse. In this work, we formulate the adversarially robust recourse problem and show that recourse methods that offer minimally costly recourse fail to be robust. We then present methods for generating adversarially robust recourse for linear and for differentiable classifiers. Finally, we show that reg…
Institute for Statistics, LMU Munich（慕尼黑大学统计研究所）；Research Group Neuroinformatics, University of Vienna（维也纳大学神经信息学研究组）；Munich Center for Mathematical Philosophy, LMU Munich（慕尼黑大学慕尼黑数学哲学中心）
Algorithmic recourse explanations inform stakeholders on how to act to revert unfavorable predictions. However, in general ML models do not predict well in interventional distributions. Thus, an action that changes the prediction in the desired way may not lead to an improvement of the underlying target. Such recourse is neither meaningful nor robust to model refits. Extending the work of Karimi et al. (2021), we propose meaningful algorithmic recourse (MAR) that only recommends actions that improve both prediction and target. We justify this selection constraint by highlighting the difference…
VinAI Research（VinAI研究（机构））；The Chinese University of Hong Kong（香港中文大学）；Vietnam（越南（此处越南作为国家名，按要求不提取，原句中“Vietnam”可能是国家名，非机构，原文本中“VinAI Research, Vietnam”的“Vietnam”可能是国家名，机构应为“VinAI Research”，“The Chinese University of Hong Kong”是机构。修正后，正确提取：[{）
Explaining algorithmic decisions and recommending actionable feedback is increasingly important for machine learning applications. Recently, significant efforts have been invested in finding a diverse set of recourses to cover the wide spectrum of users' preferences. However, existing works often neglect the requirement that the recourses should be close to the data manifold; hence, the constructed recourses might be implausible and unsatisfying to users. To address these issues, we propose a novel approach that explicitly directs the diverse set of actionable recourses towards the data manifo…
Algorithmic Recourse in Partially and Fully Confounded Settings Through Bounding Counterfactual Effects
Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；University of Cambridge（剑桥大学）；University of Tübingen（蒂宾根大学）；University College London（伦敦大学学院）
From Universal to Individualized Actionability: Revisiting Personalization in Algorithmic Recourse
Saarland Informatics Campus, Saarland University（萨尔大学萨尔兰信息学园区）；Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）；Institute for Psychology, University of Freiburg（弗莱堡大学心理学研究所）
Tübingen AI Center（图宾根人工智能中心）；University of Tübingen（图宾根大学）；Korteweg-de Vries Institute for Mathematics, University of Amsterdam（阿姆斯特丹大学科特韦德-德-弗里斯数学研究所）；LMU Munich（慕尼黑大学）；Munich Center for Machine Learning (MCML)（慕尼黑机器学习中心）；ELLIS Institute Tübingen, Max Planck Institute for Intelligent Systems, Tübingen（图宾根智能系统马克斯·普朗克研究所）
Feature attributions are a common paradigm for model explanations due to their simplicity in assigning a single numeric score for each input feature to a model. In the actionable recourse setting, wherein the goal of the explanations is to improve outcomes for model consumers, it is often unclear how feature attributions should be correctly used. With this work, we aim to strengthen and clarify the link between actionable recourse and feature attributions. Concretely, we propose a variant of SHAP, Counterfactual SHAP (CF-SHAP), that incorporates counterfactual information to produce a backgrou…
Arthur AI；University of Washington（华盛顿大学）；University of Maryland（马里兰大学）
Explainable machine learning (ML) has gained traction in recent years due to the increasing adoption of ML-based systems in many sectors. Algorithmic Recourses (ARs) provide "what if" feedback of the form "if an input datapoint were x' instead of x, then an ML-based system's output would be y' instead of y." ARs are attractive due to their actionable feedback, amenability to existing legal frameworks, and fidelity to the underlying ML model. Yet, current AR approaches are single shot -- that is, they assume x can change to x' in a single time period. We propose a novel stochastic-control-based…
University of Tübingen（图宾根大学）；University of Amsterdam（阿姆斯特丹大学）
The goal of algorithmic recourse is to reverse unfavorable decisions (e.g., from loan denial to approval) under automated decision making by suggesting actionable feature changes (e.g., reduce the number of credit cards). To generate low-cost recourse the majority of methods work under the assumption that the features are independently manipulable (IMF). To address the feature dependency issue the recourse problem is usually studied through the causal recourse paradigm. However, it is well known that strong assumptions, as encoded in causal models and structural equations, hinder the applicabi…
ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets
Princeton University（普林斯顿大学）；Ukrainian Catholic University（乌克兰天主教大学）；Rutgers University（罗格斯大学）；Taras Shevchenko National University of Kyiv（塔拉斯·谢甫琴科基斯林国立大学）；Microsoft Research NYC（微软研究院纽约）
Counterfactual explanations have been widely studied in explainability, with a range of application dependent methods emerging in fairness, recourse and model understanding. However, the major shortcoming associated with these methods is their inability to provide explanations beyond the local or instance-level. While some works touch upon the notion of a global explanation, typically suggesting to aggregate masses of local explanations in the hope of ascertaining global properties, few provide frameworks that are either reliable or computationally tractable. Meanwhile, practitioners are reque…
Reinforcement Learning for Durable Algorithmic Recourse
University of Padova（帕多瓦大学）；Univesity of Trieste（特伦蒂诺大学）；Max Planck Institute for Software Systems（马克斯·普朗克软件系统研究所）；Max Planck Institute for Security and Privacy（马克斯·普朗克安全与隐私研究所）
University of Tübingen（蒂宾根大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Algorithmic recourse aims to disclose the inner workings of the black-box decision process in situations where decisions have significant consequences, by providing recommendations to empower beneficiaries to achieve a more favorable outcome. To ensure an effective remedy, suggested interventions must not only be low-cost but also robust and fair. This goal is accomplished by providing similar explanations to individuals who are alike. This study explores the concept of individual fairness and adversarial robustness in causal algorithmic recourse and addresses the challenge of achieving both. …
Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；University of Trento（特伦托大学）
Being able to provide counterfactual interventions - sequences of actions we would have had to take for a desirable outcome to happen - is essential to explain how to change an unfavourable decision by a black-box machine learning model (e.g., being denied a loan request). Existing solutions have mainly focused on generating feasible interventions without providing explanations on their rationale. Moreover, they need to solve a separate optimization problem for each user. In this paper, we take a different approach and learn a program that outputs a sequence of explainable counterfactual actio…
Yale University（耶鲁大学）；The University of North Carolina, Chapel Hill（北卡罗来纳大学教堂山分校）；The University of Hong Kong（香港大学）；The Chinese University of Hong Kong（香港中文大学）
Actionable Interpretation of Machine Learning Models for Sequential Data: Dementia-related Agitation Use Case
University of Virginia（弗吉尼亚大学）；North Carolina A&T State University（北卡罗来纳农工州立大学）；Virginia Tech Carilion School of Medicine（弗吉尼亚理工卡里利安医学院）；The George Washington University（乔治·华盛顿大学）
Revitalizing Black-Box Interpretability: Actionable Interpretability for LLMs via Proxy Models
Key Lab of High Confidence Software Technologies (Peking University), Ministry of Education（高可信软件技术教育部重点实验室（北京大学））；School of Computer Science, Peking University（北京大学计算机学院）
End-to-end learning of dynamical systems with black-box models, such as neural ordinary differential equations (ODEs), provides a flexible framework for learning dynamics from data without prescribing a mathematical model for the dynamics. Unfortunately, this flexibility comes at the cost of understanding the dynamical system, for which ODEs are used ubiquitously. Further, experimental data are collected under various conditions (inputs), such as treatments, or grouped in some way, such as part of sub-populations. Understanding the effects of these system inputs on system outputs is crucial to…
GLANCE: Global Actions in a Nutshell for Counterfactual Explainability
Institute for the Management of Information Systems, Athena Research Center（信息管理系统研究所，雅典研究中心）；Department of Electrical and Computer Engineering, National Technical University of Athens（电气与计算机工程系，雅典技术大学）；Max Planck Institute for Software Systems（软件系统马克斯·普朗克研究所）；Université Libre de Bruxelles（布鲁塞尔自由大学）；FARI Institute, Belgium（比利时FARI研究所）；Department of Informatics, Athens University of Economics and Business（信息系，雅典经济与商业大学）；Department of Informatics and Telecommunications, National and Kapodistrian University of Athens（信息与电信系，雅典国家与卡波迪斯蒂亚大学）；Archimedes, Athena Research Center（阿基米德，雅典研究中心）
