paper-with-me

홈 › Papers

AR-Pro: Counterfactual Explanations for Anomaly Repair with Formal Properties

2024-10-31 · Xiayan Ji, Anton Xue, Eric Wong, Oleg Sokolsky, Insup Lee

Anomaly detection is widely used for identifying critical errors and suspicious behaviors, but current methods lack interpretability. We leverage common properties of existing methods and recent advances in generative models to introduce counterfactual explanations for anomaly detection. Given an input, we generate its counterfactual as a diffusion-based repair that shows what a non-anomalous version should have looked like. A key advantage of this approach is that it enables a domain-independent formal specification of explainability desiderata, offering a unified framework for generating and evaluating explanations. We demonstrate the effectiveness of our anomaly explainability framework, AR-Pro, on vision (MVTec, VisA) and time-series (SWaT, WADI, HAI) anomaly datasets. The code used for the experiments is accessible at: https://github.com/xjiae/arpro.

📄 PDF Abstract BibTeX arXiv:2410.24178

Code (1)

xjiae/arpro 공식 구현 pytorch

Tasks

Anomaly DetectioncounterfactualTime Series

Similar Papers 제목 키워드 기반

Ranking Counterfactual Explanations

2025-03-20 · Suryani Lim, Henri Prade, Gilles Richard

AI-driven outcomes can be challenging for end-users to understand. Explanations can address two key questions: "Why this outcome?" (factual) and "Why not another?" (counterfactual). While substantial efforts have been ma…

counterfactualCounterfactual Explanation

Answer-Set Programs for Repair Updates and Counterfactual Interventions

2022-09-25 · Leopoldo Bertossi

We briefly describe -- mainly through very simple examples -- different kinds of answer-set programs with annotations that have been proposed for specifying: database repairs and consistent query answering; secrecy view …

counterfactual

CE-QArg: Counterfactual Explanations for Quantitative Bipolar Argumentation Frameworks (Technical Report)

2024-07-11 · Xiang Yin, Nico Potyka, Francesca Toni

There is a growing interest in understanding arguments' strength in Quantitative Bipolar Argumentation Frameworks (QBAFs). Most existing studies focus on attribution-based methods that explain an argument's strength by a…

counterfactualvalid

Faithful Model Explanations through Energy-Constrained Conformal Counterfactuals

2023-12-17 · Patrick Altmeyer, Mojtaba Farmanbar, Arie van Deursen, Cynthia C. S. Liem

Counterfactual explanations offer an intuitive and straightforward way to explain black-box models and offer algorithmic recourse to individuals. To address the need for plausible explanations, existing work has primaril…

Conformal Predictioncounterfactual

Diverse Counterfactual Explanations for Anomaly Detection in Time Series

2022-03-21 · Deborah Sulem, Michele Donini, Muhammad Bilal Zafar, Francois-Xavier Aubet 외

Data-driven methods that detect anomalies in times series data are ubiquitous in practice, but they are in general unable to provide helpful explanations for the predictions they make. In this work we propose a model-agn…

Anomaly DetectioncounterfactualTime SeriesTime Series Analysis+1