paper-with-me

홈 › Papers

Pre or Post-Softmax Scores in Gradient-based Attribution Methods, What is Best?

2023-06-22 · Miguel Lerma, Mirtha Lucas

Gradient based attribution methods for neural networks working as classifiers use gradients of network scores. Here we discuss the practical differences between using gradients of pre-softmax scores versus post-softmax scores, and their respective advantages and disadvantages.

📄 PDF Abstract BibTeX arXiv:2306.13197

Code (1)

mlerma54/adversarial-attacks-on-saliency-maps 공식 구현

Similar Papers 제목 키워드 기반

Greedy PIG: Adaptive Integrated Gradients

2023-11-10 · Kyriakos Axiotis, Sami Abu-al-haija, Lin Chen, Matthew Fahrbach 외

Deep learning has become the standard approach for most machine learning tasks. While its impact is undeniable, interpreting the predictions of deep learning models from a human perspective remains a challenge. In contra…

Deep Learningfeature selection

A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs

2026-07-23 · Bizu Feng, Zhimu Yang, Shuming Wang, Shaode Yu 외 arxiv

We study feature-level and node-level explanations for graph neural networks (GNNs) through the lens of Aumann-Shapley attribution. Path-integral methods such as Integrated Gradients provide an axiomatic formulation of a…

A Vulnerability of Attribution Methods Using Pre-Softmax Scores

2023-07-06 · Miguel Lerma, Mirtha Lucas

We discuss a vulnerability involving a category of attribution methods used to provide explanations for the outputs of convolutional neural networks working as classifiers. It is known that this type of networks are vuln…

Towards trustworthy explanations with gradient-based attribution methods

2021-09-24 · NeurIPS Workshop AI4Scien 2021 12 · Ethan Louis Labelson, Rohit Tripathy, Peter K Koo

The low interpretability of deep neural networks (DNNs) remains a key barrier to their wide-spread adoption in the sciences. Attribution methods offer a promising solution, providing feature importance scores that serve …

Feature ImportanceModel Selectionscientific discovery

Dynamic Top-k Estimation Consolidates Disagreement between Feature Attribution Methods

2023-10-09 · Jonathan Kamp, Lisa Beinborn, Antske Fokkens

Feature attribution scores are used for explaining the prediction of a text classifier to users by highlighting a k number of tokens. In this work, we propose a way to determine the number of optimal k tokens that should…

Sentence