Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals

• URL: http://arxiv.org/abs/2103.11972v1
• Date: Mon, 22 Mar 2021 16:20:21 GMT
• Title: Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactuals
• Authors: Sainyam Galhotra, Romila Pradhan, Babak Salimi
• Abstract summary: We propose a principled causality-based approach for explaining black-box decision-making systems. We show how such counterfactuals can quantify the direct and indirect influences of a variable on decisions made by an algorithm. We show how such counterfactuals can provide actionable recourse for individuals negatively affected by the algorithm's decision.
• Score: 7.727206277914709
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: There has been a recent resurgence of interest in explainable artificial intelligence (XAI) that aims to reduce the opaqueness of AI-based decision-making systems, allowing humans to scrutinize and trust them. Prior work in this context has focused on the attribution of responsibility for an algorithm's decisions to its inputs wherein responsibility is typically approached as a purely associational concept. In this paper, we propose a principled causality-based approach for explaining black-box decision-making systems that addresses limitations of existing methods in XAI. At the core of our framework lies probabilistic contrastive counterfactuals, a concept that can be traced back to philosophical, cognitive, and social foundations of theories on how humans generate and select explanations. We show how such counterfactuals can quantify the direct and indirect influences of a variable on decisions made by an algorithm, and provide actionable recourse for individuals negatively affected by the algorithm's decision. Unlike prior work, our system, LEWIS: (1)can compute provably effective explanations and recourse at local, global and contextual levels (2)is designed to work with users with varying levels of background knowledge of the underlying causal model and (3)makes no assumptions about the internals of an algorithmic system except for the availability of its input-output data. We empirically evaluate LEWIS on three real-world datasets and show that it generates human-understandable explanations that improve upon state-of-the-art approaches in XAI, including the popular LIME and SHAP. Experiments on synthetic data further demonstrate the correctness of LEWIS's explanations and the scalability of its recourse algorithm.

Related papers

• Towards Symbolic XAI -- Explanation Through Human Understandable Logical Relationships Between Features [19.15360328688008]
  We propose a framework, called Symbolic XAI, that attributes relevance to symbolic queries expressing logical relationships between input features. The framework provides an understanding of the model's decision-making process that is both flexible for customization by the user and human-readable.
  arXiv  Detail & Related papers  (2024-08-30T10:52:18Z)
• Explaining by Imitating: Understanding Decisions by Interpretable Policy Learning [72.80902932543474]
  Understanding human behavior from observed data is critical for transparency and accountability in decision-making. Consider real-world settings such as healthcare, in which modeling a decision-maker's policy is challenging. We propose a data-driven representation of decision-making behavior that inheres transparency by design, accommodates partial observability, and operates completely offline.
  arXiv  Detail & Related papers  (2023-10-28T13:06:14Z)
• Explaining Explainability: Towards Deeper Actionable Insights into Deep Learning through Second-order Explainability [70.60433013657693]
  Second-order explainable AI (SOXAI) was recently proposed to extend explainable AI (XAI) from the instance level to the dataset level. We demonstrate for the first time, via example classification and segmentation cases, that eliminating irrelevant concepts from the training set based on actionable insights from SOXAI can enhance a model's performance.
  arXiv  Detail & Related papers  (2023-06-14T23:24:01Z)
• Towards Human Cognition Level-based Experiment Design for Counterfactual Explanations (XAI) [68.8204255655161]
  The emphasis of XAI research appears to have turned to a more pragmatic explanation approach for better understanding. An extensive area where cognitive science research may substantially influence XAI advancements is evaluating user knowledge and feedback. We propose a framework to experiment with generating and evaluating the explanations on the grounds of different cognitive levels of understanding.
  arXiv  Detail & Related papers  (2022-10-31T19:20:22Z)
• Neural Causal Models for Counterfactual Identification and Estimation [62.30444687707919]
  We study the evaluation of counterfactual statements through neural models. First, we show that neural causal models (NCMs) are expressive enough. Second, we develop an algorithm for simultaneously identifying and estimating counterfactual distributions.
  arXiv  Detail & Related papers  (2022-09-30T18:29:09Z)
• Causal Fairness Analysis [68.12191782657437]
  We introduce a framework for understanding, modeling, and possibly solving issues of fairness in decision-making settings. The main insight of our approach will be to link the quantification of the disparities present on the observed data with the underlying, and often unobserved, collection of causal mechanisms. Our effort culminates in the Fairness Map, which is the first systematic attempt to organize and explain the relationship between different criteria found in the literature.
  arXiv  Detail & Related papers  (2022-07-23T01:06:34Z)
• From Cognitive to Computational Modeling: Text-based Risky Decision-Making Guided by Fuzzy Trace Theory [5.154015755506085]
  Fuzzy trace theory (FTT) is a powerful paradigm that explains human decision-making by incorporating gists. We propose a computational framework which combines the effects of the underlying semantics and sentiments on text-based decision-making. In particular, we introduce Category-2- to learn categorical gists and categorical sentiments, and demonstrate how our computational model can be optimised to predict risky decision-making in groups and individuals.
  arXiv  Detail & Related papers  (2022-05-15T02:25:28Z)
• The Conflict Between Explainable and Accountable Decision-Making Algorithms [10.64167691614925]
  Decision-making algorithms are being used in important decisions, such as who should be enrolled in health care programs and be hired. XAI initiative aims to make algorithms explainable to comply with legal requirements, promote trust, and maintain accountability. This paper questions whether and to what extent explainability can help solve the responsibility issues posed by autonomous AI systems.
  arXiv  Detail & Related papers  (2022-05-11T07:19:28Z)
• Deep Learning Reproducibility and Explainable AI (XAI) [9.13755431537592]
  The nondeterminism of Deep Learning (DL) training algorithms and its influence on the explainability of neural network (NN) models are investigated. To discuss the issue, two convolutional neural networks (CNN) have been trained and their results compared.
  arXiv  Detail & Related papers  (2022-02-23T12:06:20Z)
• Counterfactual Explanations as Interventions in Latent Space [62.997667081978825]
  Counterfactual explanations aim to provide to end users a set of features that need to be changed in order to achieve a desired outcome. Current approaches rarely take into account the feasibility of actions needed to achieve the proposed explanations. We present Counterfactual Explanations as Interventions in Latent Space (CEILS), a methodology to generate counterfactual explanations.
  arXiv  Detail & Related papers  (2021-06-14T20:48:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.