paper-with-me

홈 › Papers

AttributionLab: Faithfulness of Feature Attribution Under Controllable Environments

2023-10-10 · Yang Zhang, Yawei Li, Hannah Brown, Mina Rezaei, Bernd Bischl, Philip Torr, Ashkan Khakzar, Kenji Kawaguchi

Feature attribution explains neural network outputs by identifying relevant input features. The attribution has to be faithful, meaning that the attributed features must mirror the input features that influence the output. One recent trend to test faithfulness is to fit a model on designed data with known relevant features and then compare attributions with ground truth input features.This idea assumes that the model learns to use all and only these designed features, for which there is no guarantee. In this paper, we solve this issue by designing the network and manually setting its weights, along with designing data. The setup, AttributionLab, serves as a sanity check for faithfulness: If an attribution method is not faithful in a controlled environment, it can be unreliable in the wild. The environment is also a laboratory for controlled experiments by which we can analyze attribution methods and suggest improvements.

📄 PDF Abstract BibTeX arXiv:2310.06514

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

On Understanding the Influence of Controllable Factors with a Feature Attribution Algorithm: a Medical Case Study

2022-03-23 · Veera Raghava Reddy Kovvuri, Siyuan Liu, Monika Seisenberger, Berndt Müller 외

Feature attribution XAI algorithms enable their users to gain insight into the underlying patterns of large datasets through their feature importance calculation. Existing feature attribution algorithms treat all feature…

Explainable Artificial Intelligence (XAI)Feature Importance

Towards a Theory of Faithfulness: Faithful Explanations of Differentiable Classifiers over Continuous Data

2022-05-19 · Nico Potyka, Xiang Yin, Francesca Toni

There is broad agreement in the literature that explanation methods should be faithful to the model that they explain, but faithfulness remains a rather vague term. We revisit faithfulness in the context of continuous da…

PhaseWin: An Efficient Search Algorithm for Faithful Visual Attribution

2026-06-16 · Zihan Gu, Junchi Zhang, Li Liu, Xiaochun Cao 외 arxiv

Visual attribution is a fundamental tool for interpreting modern vision and vision-language models, particularly when their decisions must be inspected, diagnosed, or audited. Its goal is to explain how a model's decisio…

Image ClassificationImage CaptioningObject DetectionVisual Grounding

A Dual-Perspective Approach to Evaluating Feature Attribution Methods

2023-08-17 · Yawei Li, Yang Zhang, Kenji Kawaguchi, Ashkan Khakzar 외

Feature attribution methods attempt to explain neural network predictions by identifying relevant features. However, establishing a cohesive framework for assessing feature attribution remains a challenge. There are seve…

Normalized AOPC: Fixing Misleading Faithfulness Metrics for Feature Attribution Explainability

2024-08-15 · Joakim Edin, Andreas Geert Motzfeldt, Casper L. Christensen, Tuukka Ruotsalo 외

Deep neural network predictions are notoriously difficult to interpret. Feature attribution methods aim to explain these predictions by identifying the contribution of each input feature. Faithfulness, often evaluated us…