paper-with-me

홈 › Papers

Fast Explanations via Policy Gradient-Optimized Explainer

2024-05-29 · Deng Pan, Nuno Moniz, Nitesh Chawla

The challenge of delivering efficient explanations is a critical barrier that prevents the adoption of model explanations in real-world applications. Existing approaches often depend on extensive model queries for sample-level explanations or rely on expert's knowledge of specific model structures that trade general applicability for efficiency. To address these limitations, this paper introduces a novel framework Fast Explanation (FEX) that represents attribution-based explanations via probability distributions, which are optimized by leveraging the policy gradient method. The proposed framework offers a robust, scalable solution for real-time, large-scale model explanations, bridging the gap between efficiency and applicability. We validate our framework on image and text classification tasks and the experiments demonstrate that our method reduces inference time by over 97% and memory usage by 70% compared to traditional model-agnostic approaches while maintaining high-quality explanations and broad applicability.

📄 PDF Abstract BibTeX arXiv:2405.18664

Code (0)

등록된 구현이 없습니다.

Tasks

text-classificationText Classification

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically

Similar Papers 제목 키워드 기반

FastSHAP: Real-Time Shapley Value Estimation

2021-07-15 · ICLR 2022 4 · Neil Jethani, Mukund Sudarshan, Ian Covert, Su-In Lee 외

Shapley values are widely used to explain black-box models, but they are costly to calculate because they require many model evaluations. We introduce FastSHAP, a method for estimating Shapley values in a single forward …

Reinforced Causal Explainer for Graph Neural Networks

2022-04-23 · Xiang Wang, Yingxin Wu, An Zhang, Fuli Feng 외

Explainability is crucial for probing graph neural networks (GNNs), answering questions like "Why the GNN model makes a certain prediction?". Feature attribution is a prevalent technique of highlighting the explanatory s…

Graph Classification

Explaining GNN Explanations with Edge Gradients

2025-08-01 · Jesse He, Akbar Rafiey, Gal Mishne, Yusu Wang arxiv

In recent years, the remarkable success of graph neural networks (GNNs) on graph-structured data has prompted a surge of methods for explaining GNN predictions. However, the state-of-the-art for GNN explainability remain…

Graph Reconstruction from Differentially Private GNN Explanations

2026-05-05 · Rishi Raj Sahoo, Jyotirmaya Shivottam, Subhankar Mishra arxiv

Regulatory frameworks such as GDPR increasingly require that ML predictions be accompanied by post-hoc explanations, even when raw data and trained models cannot be released. Differential privacy (DP) is the standard mit…

T-Explainer: A Model-Agnostic Explainability Framework Based on Gradients

2024-04-25 · Evandro S. Ortigossa, Fábio F. Dias, Brian Barr, Claudio T. Silva 외

The development of machine learning applications has increased significantly in recent years, motivated by the remarkable ability of learning-powered systems to discover and generalize intricate patterns hidden in massiv…

Decision MakingExplainable artificial intelligenceExplainable Artificial Intelligence (XAI)