Graph Neural Network Explanation

Explaining the predictions of Graph Neural Networks (GNNs) is crucial for building trust and understanding in their applications. Current research focuses on developing robust explanation methods, including those based on motif identification and counterfactual reasoning, while simultaneously addressing the challenge of evaluating explanation quality and their vulnerability to adversarial attacks. Improved GNN explainability is vital for enhancing the reliability and adoption of GNNs across diverse scientific fields and practical applications, particularly where interpretability is paramount, such as in drug discovery or social network analysis.

Papers

June 5, 2024

Graph Neural Network Explanations are Fragile
Jiate Li, Meng Pang, Yun Dong, Jinyuan Jia, Binghui Wang
Graph Neural Network Adversarial Attack Graph Neural Network Explanation

May 21, 2024

MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation
Zhaoning Yu, Hongyang Gao
Graph Neural Network Molecular Graph Molecular Data Graph Neural Network Explanation Motif Based Graph

May 11, 2024

Design Requirements for Human-Centered Graph Neural Network Explanations
Pantea Habibi, Peyman Baghershahi, Sourav Medya, Debaleena Chattopadhyay
Graph Neural Network Graph Learning GNN Explanation GNN Explainers Design Consideration Human Understandable Explanation Graph Neural Network Explanation

September 28, 2023

GInX-Eval: Towards In-Distribution Evaluation of Graph Neural Network Explanations
Kenza Amara, Mennatallah El-Assady, Rex Ying
Ground Truth Explainability Method G Eval Graph Explainability Distribution Input Explainable Graph Graph Neural Network Explanation

January 7, 2023

Faithful and Consistent Graph Neural Network Explanations with Rationale Alignment
Tianxiang Zhao, Dongsheng Luo, Xiang Zhang, Suhang Wang
Inductive Bias Instance Level Distribution Alignment Faithful Explanation Rationale Alignment Graph Neural Network Explanation

June 28, 2022

BAGEL: A Benchmark for Assessing Graph Neural Network Explanations
Mandeep Rathee, Thorben Funke, Avishek Anand, Megha Khosla
New Benchmark Interpretability Method GNN Explanation Graph Neural Network Explanation

February 17, 2022

Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoning
Juntao Tan, Shijie Geng, Zuohui Fu, Yingqiang Ge, Shuyuan Xu, Yunqi Li, Yongfeng Zhang
LeArning Abstract Graph Neural Network Ground Truth GNN Explainers Graph Neural Network Explanation

November 25, 2021

Demystifying Graph Neural Network Explanations
Anna Himmelhuber, Mitchell Joblin, Martin Ringsquandl, Thomas Runkler
Neural Network Graph Neural Network Graph Drawing Synthetic Data Generation Perturbation Analysis Graph Neural Network Explanation