paper-with-me

Papers

CARE: Coherent Actionable Recourse based on Sound Counterfactual Explanations

2021-08-18 · Peyman Rasouli, Ingrid Chieh Yu

Counterfactual explanation methods interpret the outputs of a machine learning model in the form of "what-if scenarios" without compromising the fidelity-interpretability trade-off. They explain how to obtain a desired prediction from the model by recommending small changes to the input features, aka recourse. We believe an actionable recourse should be created based on sound counterfactual explanations originating from the distribution of the ground-truth data and linked to the domain knowledge. Moreover, it needs to preserve the coherency between changed/unchanged features while satisfying user/domain-specified constraints. This paper introduces CARE, a modular explanation framework that addresses the model- and user-level desiderata in a consecutive and structured manner. We tackle the existing requirements by proposing novel and efficient solutions that are formulated in a multi-objective optimization framework. The designed framework enables including arbitrary requirements and generating counterfactual explanations and actionable recourse by choice. As a model-agnostic approach, CARE generates multiple, diverse explanations for any black-box model in tabular classification and regression settings. Several experiments on standard data sets and black-box models demonstrate the effectiveness of our modular framework and its superior performance compared to the baselines.

📄 PDF Abstract BibTeX arXiv:2108.08197

Code (1)

peymanrasouli/care 공식 구현 pytorch

Tasks

counterfactualCounterfactual ExplanationExplainable artificial intelligencetabular-classification

Similar Papers 제목 키워드 기반

Counterfactual Explanations via Locally-guided Sequential Algorithmic Recourse

2023-09-08 · Edward A. Small, Jeffrey N. Clark, Christopher J. McWilliams, Kacper Sokol 외

Counterfactuals operationalised through algorithmic recourse have become a powerful tool to make artificial intelligence systems explainable. Conceptually, given an individual classified as y -- the factual -- we seek ac…

counterfactual

Counterfactual Shapley Additive Explanations

2021-10-27 · Emanuele Albini, Jason Long, Danial Dervovic, Daniele Magazzeni

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…

counterfactualCounterfactual ExplanationExplainable artificial intelligenceFeature Importance

FACE: Feasible and Actionable Counterfactual Explanations

2019-09-20 · Rafael Poyiadzi, Kacper Sokol, Raul Santos-Rodriguez, Tijl De Bie 외

Work in Counterfactual Explanations tends to focus on the principle of "the closest possible world" that identifies small changes leading to the desired outcome. In this paper we argue that while this approach might init…

counterfactual

Actionable CBFI: Integrating Structural Decomposition and Causal Counterfactual Recourse for Tabular Machine Learning

2026-08-28 · Sejong Oh arxiv

Explainable artificial intelligence (XAI) increasingly calls for actionable counterfactual recourse, yet current methodologies face challenges related to causal invalidity, excessive cognitive burden, and predictive fail…

Feature Importance

When Bits Break Recourse: Counterfactual-Faithful Quantization

2026-05-16 · Chaymae Yahyati, Ismail Lamaakal, Khalid El Makkaoui, Ibrahim Ouahbi arxiv

Quantization can preserve predictive accuracy under low-bit deployment while silently breaking algorithmic recourse: an actionable change that flips a decision before quantization may fail after quantization, or become s…