paper-with-me

홈 › Papers

Rethinking Distance Metrics for Counterfactual Explainability

2024-10-18 · Joshua Nathaniel Williams, Anurag Katakkar, Hoda Heidari, J. Zico Kolter

Counterfactual explanations have been a popular method of post-hoc explainability for a variety of settings in Machine Learning. Such methods focus on explaining classifiers by generating new data points that are similar to a given reference, while receiving a more desirable prediction. In this work, we investigate a framing for counterfactual generation methods that considers counterfactuals not as independent draws from a region around the reference, but as jointly sampled with the reference from the underlying data distribution. Through this framing, we derive a distance metric, tailored for counterfactual similarity that can be applied to a broad range of settings. Through both quantitative and qualitative analyses of counterfactual generation methods, we show that this framing allows us to express more nuanced dependencies among the covariates.

📄 PDF Abstract BibTeX arXiv:2410.14522

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactual

Methods 이 논문이 사용한 방법론

Focus 설명 없음
Counterfactuals 설명 없음

Similar Papers 제목 키워드 기반

A Completion-Aware Framework for Impactful Counterfactual Explainability in Graph Neural Networks

2026-06-20 · Maria Myrto Villia, Filippos Gouidis, Theodore Patkos, Panos Trahanias arxiv

In this study, we propose a novel pipeline for generic, model-agnostic, local-level counterfactual explainability in graph neural networks (GNNs). Although counterfactual explainers capable of both adding and removing ed…

Explanation GenerationGraph ClassificationLink Prediction

Shapelet-based Model-agnostic Counterfactual Local Explanations for Time Series Classification

2024-02-02 · Qi Huang, Wei Chen, Thomas Bäck, Niki van Stein

In this work, we propose a model-agnostic instance-based post-hoc explainability method for time series classification. The proposed algorithm, namely Time-CF, leverages shapelets and TimeGAN to provide counterfactual ex…

ClassificationcounterfactualTime SeriesTime Series Classification

Counterfactual Multi-player Bandits for Explainable Recommendation Diversification

2025-05-27 · Yansen Zhang, Bowei He, Xiaokun Zhang, Haolun Wu 외

Existing recommender systems tend to prioritize items closely aligned with users' historical interactions, inevitably trapping users in the dilemma of ``filter bubble''. Recent efforts are dedicated to improving the dive…

counterfactualDiversityExplainable RecommendationRecommendation Systems

Do Metrics for Counterfactual Explanations Align with User Perception?

2026-03-16 · Felix Liedeker, Basil Ell, Philipp Cimiano, Christoph Düsing arxiv

Explainability is widely regarded as essential for trustworthy artificial intelligence systems. However, the metrics commonly used to evaluate counterfactual explanations are algorithmic evaluation metrics that are rarel…

Graph Edits for Counterfactual Explanations: A comparative study

2024-01-21 · Angeliki Dimitriou, Nikolaos Chaidos, Maria Lymperaiou, Giorgos Stamou

Counterfactuals have been established as a popular explainability technique which leverages a set of minimal edits to alter the prediction of a classifier. When considering conceptual counterfactuals on images, the edits…

counterfactualGraph Neural NetworkKnowledge Graphs