paper-with-me

홈 › Papers

Counterfactual explainability of black-box prediction models

2024-11-03 · Zijun Gao, Qingyuan Zhao

It is crucial to be able to explain black-box prediction models to use them effectively and safely in practice. Most existing tools for model explanations are associational rather than causal, and we use two paradoxical examples to show that such explanations are generally inadequate. Motivated by the concept of genetic heritability in twin studies, we propose a new notion called counterfactual explainability for black-box prediction models. Counterfactual explainability has three key advantages: (1) it leverages counterfactual outcomes and extends methods for global sensitivity analysis (such as functional analysis of variance and Sobol's indices) to a causal setting; (2) it is defined not only for the totality of a set of input factors but also for their interactions (indeed, it is a probability measure on a whole ``explanation algebra''); (3) it also applies to dependent input factors whose causal relationship can be modeled by a directed acyclic graph, thus incorporating causal mechanisms into the explanation.

📄 PDF Abstract BibTeX arXiv:2411.01625

Code (0)

등록된 구현이 없습니다.

Tasks

counterfactualPrediction

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

Explainable bank failure prediction models: Counterfactual explanations to reduce the failure risk

2024-07-14 · Seyma Gunonu, Gizem Altun, Mustafa Cavus

The accuracy and understandability of bank failure prediction models are crucial. While interpretable models like logistic regression are favored for their explainability, complex models such as random forest, support ve…

counterfactualCounterfactual Explanation

Causal Proxy Models for Concept-Based Model Explanations

2022-09-28 · Zhengxuan Wu, Karel D'Oosterlinck, Atticus Geiger, Amir Zur 외

Explainability methods for NLP systems encounter a version of the fundamental problem of causal inference: for a given ground-truth input text, we never truly observe the counterfactual texts necessary for isolating the …

Causal Inferencecounterfactualmodel

Feature-based Learning for Diverse and Privacy-Preserving Counterfactual Explanations

2022-09-27 · Vy Vo, Trung Le, Van Nguyen, He Zhao 외

Interpretable machine learning seeks to understand the reasoning process of complex black-box systems that are long notorious for lack of explainability. One flourishing approach is through counterfactual explanations, w…

counterfactualDiversityfeature selectionInterpretable Machine Learning+2

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

Counterfactual Explanations for Deep Learning-Based Traffic Forecasting

2024-05-01 · Rushan Wang, Yanan Xin, Yatao Zhang, Fernando Perez-Cruz 외

Deep learning models are widely used in traffic forecasting and have achieved state-of-the-art prediction accuracy. However, the black-box nature of those models makes the results difficult to interpret by users. This st…

counterfactualDeep Learning