paper-with-me

Papers

Explainability in Graph Neural Networks: An Experimental Survey

2022-03-17 · Peibo Li, Yixing Yang, Maurice Pagnucco, Yang song

Graph neural networks (GNNs) have been extensively developed for graph representation learning in various application domains. However, similar to all other neural networks models, GNNs suffer from the black-box problem as people cannot understand the mechanism underlying them. To solve this problem, several GNN explainability methods have been proposed to explain the decisions made by GNNs. In this survey, we give an overview of the state-of-the-art GNN explainability methods and how they are evaluated. Furthermore, we propose a new evaluation metric and conduct thorough experiments to compare GNN explainability methods on real world datasets. We also suggest future directions for GNN explainability.

📄 PDF Abstract BibTeX arXiv:2203.09258

Code (0)

등록된 구현이 없습니다.

Tasks

Graph Representation LearningRepresentation LearningSurvey

Similar Papers 제목 키워드 기반

Recent Advances in Malware Detection: Graph Learning and Explainability

2025-02-14 · Hossein Shokouhinejad, Roozbeh Razavi-Far, Hesamodin Mohammadian, Mahdi Rabbani 외

The rapid evolution of malware has necessitated the development of sophisticated detection methods that go beyond traditional signature-based approaches. Graph learning techniques have emerged as powerful tools for model…

Feature EngineeringGraph EmbeddingGraph LearningMalware Analysis+2

Explainability in Graph Neural Networks: A Taxonomic Survey

2020-12-31 · Hao Yuan, Haiyang Yu, Shurui Gui, Shuiwang Ji

Deep learning methods are achieving ever-increasing performance on many artificial intelligence tasks. A major limitation of deep models is that they are not amenable to interpretability. This limitation can be circumven…

Survey

A Survey on Explainability of Graph Neural Networks

2023-06-02 · Jaykumar Kakkad, Jaspal Jannu, Kartik Sharma, Charu Aggarwal 외

Graph neural networks (GNNs) are powerful graph-based deep-learning models that have gained significant attention and demonstrated remarkable performance in various domains, including natural language processing, drug di…

Drug DiscoveryRecommendation SystemsSurvey

A Survey of Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection

2022-05-20 · Bingzhe Wu, Jintang Li, Junchi Yu, Yatao Bian 외

Deep graph learning has achieved remarkable progresses in both business and scientific areas ranging from finance and e-commerce, to drug and advanced material discovery. Despite these progresses, how to ensure various d…

Graph Learning

Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlooks

2024-10-03 · Junlin Hou, Sicen Liu, Yequan Bie, Hongmei Wang 외

The increasing demand for transparent and reliable models, particularly in high-stakes decision-making areas such as medical image analysis, has led to the emergence of eXplainable Artificial Intelligence (XAI). Post-hoc…

counterfactualCounterfactual ExplanationDecision MakingExplainable artificial intelligence+3