paper-with-me

홈 › Papers

Baseline Computation for Attribution Methods Based on Interpolated Inputs

2022-04-13 · Miguel Lerma, Mirtha Lucas

We discuss a way to find a well behaved baseline for attribution methods that work by feeding a neural network with a sequence of interpolated inputs between two given inputs. Then, we test it with our novel Riemann-Stieltjes Integrated Gradient-weighted Class Activation Mapping (RSI-Grad-CAM) attribution method.

📄 PDF Abstract BibTeX arXiv:2204.06120

Code (1)

mlerma54/RSIGradCAM 공식 구현 tf

Similar Papers 제목 키워드 기반

Discretized Integrated Gradients for Explaining Language Models

2021-08-31 · EMNLP 2021 11 · Soumya Sanyal, Xiang Ren

As a prominent attribution-based explanation algorithm, Integrated Gradients (IG) is widely adopted due to its desirable explanation axioms and the ease of gradient computation. It measures feature importance by averagin…

Feature ImportanceSentiment AnalysisSentiment Classification

Calibrating Attribution Proxies for Reward Allocation in Participatory Weather Sensing

2026-04-30 · Mark C. Ballandies, Michael T. C. Chiu, Claudio J. Tessone arxiv

Large-scale IoT weather sensing networks require incentive mechanisms to sustain participation, yet determining how much value individual data contributions bring to the network remains an open problem. Existing approach…

Automated Attribution and Intertextual Analysis

2014-05-03 · James Brofos, Ajay Kannan, Rui Shu

In this work, we employ quantitative methods from the realm of statistics and machine learning to develop novel methodologies for author attribution and textual analysis. In particular, we develop techniques and software…

Author AttributionAuthorship AttributionBIG-bench Machine Learning

Attribution-driven Causal Analysis for Detection of Adversarial Examples

2019-03-14 · Susmit Jha, Sunny Raj, Steven Lawrence Fernandes, Sumit Kumar Jha 외

Attribution methods have been developed to explain the decision of a machine learning model on a given input. We use the Integrated Gradient method for finding attributions to define the causal neighborhood of an input b…

Adversarial AttackBIG-bench Machine Learning

Rethinking Robustness: A New Approach to Evaluating Feature Attribution Methods

2025-12-07 · Panagiota Kiourti, Anu Singh, Preeti Duraipandian, Weichao Zhou 외 arxiv

This paper studies the robustness of feature attribution methods for deep neural networks. It challenges the current notion of attributional robustness that largely ignores the difference in the model's outputs and intro…