paper-with-me

홈 › Papers

Pattern-Guided Integrated Gradients

2020-07-21 · Robert Schwarzenberg, Steffen Castle

Integrated Gradients (IG) and PatternAttribution (PA) are two established explainability methods for neural networks. Both methods are theoretically well-founded. However, they were designed to overcome different challenges. In this work, we combine the two methods into a new method, Pattern-Guided Integrated Gradients (PGIG). PGIG inherits important properties from both parent methods and passes stress tests that the originals fail. In addition, we benchmark PGIG against nine alternative explainability approaches (including its parent methods) in a large-scale image degradation experiment and find that it outperforms all of them.

📄 PDF Abstract BibTeX arXiv:2007.10685

Code (1)

DFKI-NLP/pgig 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Manifold-Aligned Guided Integrated Gradients for Reliable Feature Attribution

2026-05-04 · Soyeon Kim, Seongwoo Lim, Kyowoon Lee, Jaesik Choi arxiv

Feature attribution is central to diagnosing and trusting deep neural networks, and Integrated Gradients (IG) is widely used due to its axiomatic properties. However, IG can yield unreliable explanations when the integra…

Geometrically Guided Integrated Gradients

2022-06-13 · Md Mahfuzur Rahman, Noah Lewis, Sergey Plis

Interpretability methods for deep neural networks mainly focus on the sensitivity of the class score with respect to the original or perturbed input, usually measured using actual or modified gradients. Some methods also…

Guided Integrated Gradients: An Adaptive Path Method for Removing Noise

2021-06-17 · CVPR 2021 1 · Andrei Kapishnikov, Subhashini Venugopalan, Besim Avci, Ben Wedin 외

Integrated Gradients (IG) is a commonly used feature attribution method for deep neural networks. While IG has many desirable properties, the method often produces spurious/noisy pixel attributions in regions that are no…

Diffusion Integrated Gradients: Controllable Path Generation for Flexible Feature Attribution

2026-06-21 · Soyeon Kim, Kyowoon Lee, Jaesik Choi arxiv

Path-based attribution methods such as Integrated Gradients (IG) are widely adopted for their strong axiomatic properties and effectiveness in attributing model predictions to input features by integrating gradients alon…

Integrated Decision Gradients: Compute Your Attributions Where the Model Makes Its Decision

2023-05-31 · Chase Walker, Sumit Jha, Kenny Chen, Rickard Ewetz

Attribution algorithms are frequently employed to explain the decisions of neural network models. Integrated Gradients (IG) is an influential attribution method due to its strong axiomatic foundation. The algorithm is ba…