Towards Faithful Graph Explanations with Synergistic Edge Effects via Granular Balls
Not on the map. Why?
Abstract (arXiv)
Instance-level explanations aim to reveal the rationale behind a model's decisions for a specific graph. Previous methods explain graph neural networks (GNNs) by selecting important edges to induce subgraphs, where edge importance is assessed by perturbing each edge and observing changes in the model predictions. However, they often neglect the synergistic effects among edges, which are crucial for accurately characterizing edge importance. To address this issue, we propose SeeExplainer, a parameter-free explainer to interpret GNNs. Specifically, we first introduce a granular-ball graph refinement mechanism that decomposes a graph into several disjoint granular-balls with no fixed size, and utilize them as nodes to construct a structural graph. This process can better capture the synergistic effects among edges. Then, we perturb nodes and edges in the structural graph to generate explanatory subgraphs based on their respective contributions. Experiments on several graph classification datasets of different networks show that SeeExplainer outperforms state-of-the-art baselines.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 28 of its 54 references that are in the map. First posted on arXiv 23 Jul 2026.
Builds on
28 of 54 references.
References · 28
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2018How Powerful are Graph Neural Networks?cited by 4,393
- 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
- 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 728
- 2020Parameterized Explainer for Graph Neural Networkcited by 426
- 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
- 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
- 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
- 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
- 2019Explainability Techniques for Graph Convolutional Networkscited by 161
- 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
- 2021GraphSVX: Shapley Value Explanations for Graph Neural Networkscited by 64
16 more
- 2017Towards better understanding of gradient-based attribution methods for Deep Neural Networkscited by 54
- 2020RelEx: A Model-Agnostic Relational Model Explainercited by 53
- 2022GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Gamescited by 42
- 2021Online Graph Dictionary Learningcited by 37
- 2021Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networkscited by 35
- 2022GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networkscited by 34
- 2022An Efficient and Adaptive Granular-ball Generation Method in Classification Problemcited by 33
- 2023Distill n' Explain: explaining graph neural networks using simple surrogatescited by 18
- 2023DEGREE: Decomposition Based Explanation For Graph Neural Networkscited by 18
- 2022A Unified Granular-ball Learning Model of Pawlak Rough Set and Neighborhood Rough Setcited by 12
- 2024Graph Coarsening via Supervised Granular-Ball for Scalable Graph Neural Network Trainingcited by 9
- 2024GB-RVFL: Fusion of Randomized Neural Network and Granular Ball Computingcited by 7
- 2024EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Timecited by 5
- 2024Generation of Granular-Balls for Clustering Based on the Principle of Justifiable Granularitycited by 4
- 2024Edge Classification on Graphs: New Directions in Topological Imbalancecited by 4
- 2025Fuzzy Granule Density-Based Outlier Detection with Multi-Scale Granular Ballscited by 3
Built on by
Not cited yet.