paper-with-me

Papers

Investigating Saturation Effects in Integrated Gradients

2020-10-23 · Vivek Miglani, Narine Kokhlikyan, Bilal Alsallakh, Miguel Martin, Orion Reblitz-Richardson

Integrated Gradients has become a popular method for post-hoc model interpretability. De-spite its popularity, the composition and relative impact of different regions of the integral path are not well understood. We explore these effects and find that gradients in saturated regions of this path, where model output changes minimally, contribute disproportionately to the computed attribution. We propose a variant of IntegratedGradients which primarily captures gradients in unsaturated regions and evaluate this method on ImageNet classification networks. We find that this attribution technique shows higher model faithfulness and lower sensitivity to noise com-pared with standard Integrated Gradients. A note-book illustrating our computations and results is available at https://github.com/vivekmig/captum-1/tree/ExpandedIG.

📄 PDF Abstract BibTeX arXiv:2010.12697

Code (1)

vivekmig/captum-1 공식 구현 pytorch

Tasks

Sensitivity

Similar Papers 제목 키워드 기반

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…

FRInGe: Distribution-Space Integrated Gradients with Fisher--Rao Geometry

2026-05-07 · Gabriele Martino, Sebastian Tschiatschek arxiv

Gradient-based attribution methods are model-faithful and scalable, but Integrated Gradients (IG) can be brittle because explanations depend on heuristic baselines, straight-line paths, discretization, and saturation. We…

Expected Grad-CAM: Towards gradient faithfulness

2024-06-03 · Vincenzo Buono, Peyman Sheikholharam Mashhadi, Mahmoud Rahat, Prayag Tiwari 외

Although input-gradients techniques have evolved to mitigate and tackle the challenges associated with gradients, modern gradient-weighted CAM approaches still rely on vanilla gradients, which are inherently susceptible …

counterfactualSensitivity

AnglE-optimized Text Embeddings

2023-09-22 · Xianming Li, Jing Li

High-quality text embedding is pivotal in improving semantic textual similarity (STS) tasks, which are crucial components in Large Language Model (LLM) applications. However, a common challenge existing text embedding mo…

Language ModellingLarge Language ModelSemantic Textual SimilaritySentiment Analysis+1

New possibilities in identification of binary choice models with fixed effects

2022-06-21 · Yinchu Zhu

We study the identification of binary choice models with fixed effects. We propose a condition called sign saturation and show that this condition is sufficient for identifying the model. In particular, this condition ca…