Rethinking Distance Metrics for Counterfactual Explainability
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.
Code (0)
등록된 구현이 없습니다.
Tasks
counterfactualMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
A Completion-Aware Framework for Impactful Counterfactual Explainability in Graph Neural Networks
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 PredictionShapelet-based Model-agnostic Counterfactual Local Explanations for Time Series Classification
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 ClassificationCounterfactual Multi-player Bandits for Explainable Recommendation Diversification
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 SystemsDo Metrics for Counterfactual Explanations Align with User Perception?
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
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