paper-with-me

Papers

Non-Uniform Interpolation in Integrated Gradients for Low-Latency Explainable-AI

2023-02-22 · Ashwin Bhat, Arijit Raychowdhury

There has been a surge in Explainable-AI (XAI) methods that provide insights into the workings of Deep Neural Network (DNN) models. Integrated Gradients (IG) is a popular XAI algorithm that attributes relevance scores to input features commensurate with their contribution to the model's output. However, it requires multiple forward \& backward passes through the model. Thus, compared to a single forward-pass inference, there is a significant computational overhead to generate the explanation which hinders real-time XAI. This work addresses the aforementioned issue by accelerating IG with a hardware-aware algorithm optimization. We propose a novel non-uniform interpolation scheme to compute the IG attribution scores which replaces the baseline uniform interpolation. Our algorithm significantly reduces the total interpolation steps required without adversely impacting convergence. Experiments on the ImageNet dataset using a pre-trained InceptionV3 model demonstrate \textit{2.6-3.6}$\times$ performance speedup on GPU systems for iso-convergence. This includes the minimal \textit{0.2-3.2}\% latency overhead introduced by the pre-processing stage of computing the non-uniform interpolation step-sizes.

📄 PDF Abstract BibTeX arXiv:2302.11107

Code (0)

등록된 구현이 없습니다.

Tasks

Explainable Artificial Intelligence (XAI)GPU

Similar Papers 제목 키워드 기반

Path-Sampled Integrated Gradients

2026-04-15 · Firuz Kamalov, Fadi Thabtah, R. Sivaraj, Neda Abdelhamid arxiv

We introduce path-sampled integrated gradients (PS-IG), a framework that generalizes feature attribution by computing the expected value over baselines sampled along the linear interpolation path. We prove that PS-IG is …

Uniform Discretized Integrated Gradients: An effective attribution based method for explaining large language models

2024-12-05 · Swarnava Sinha Roy, Ayan Kundu

Integrated Gradients is a well-known technique for explaining deep learning models. It calculates feature importance scores by employing a gradient based approach computing gradients of the model output with respect to i…

BenchmarkingFeature ImportanceQuestion AnsweringSentiment Analysis+2

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

Riemannian Integrated Gradients: A Geometric View of Explainable AI

2025-03-02 · Federico Costanza, Lachlan Simpson

We introduce Riemannian Integrated Gradients (RIG); an extension of Integrated Gradients (IG) to Riemannian manifolds. We demonstrate that RIG restricts to IG when the Riemannian manifold is Euclidean space. We show that…

Weighted Average Gradients for Feature Attribution

2025-05-06 · Kien Tran Duc Tuan, Tam Nguyen Trong, Son Nguyen Hoang, Khoat Than 외

In explainable AI, Integrated Gradients (IG) is a widely adopted technique for assessing the significance of feature attributes of the input on model outputs by evaluating contributions from a baseline input to the curre…