ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule mining
Not on the map. Why?
Abstract (arXiv)
Numerous graph neural network (GNN)-based algorithms have been proposed to solve graph-based combinatorial optimization problems (COPs), but methods to explain their predictions remain largely undeveloped. We introduce ARM-Explainer, a post-hoc, model-level explainer based on association rule mining, and demonstrate it on the predictions of the hybrid geometric scattering (HGS) GNN for the maximum clique problem (MCP), a canonical NP-hard graph-based COP. The eight most explanatory association rules discovered by ARM-Explainer achieve high median lift and confidence values of 2.42 and 0.49, respectively, on test instances from the TWITTER and BHOSLIB-DIMACS benchmark datasets. ARM-Explainer identifies the most important node features, together with their value ranges, that influence the GNN's predictions on these datasets. Furthermore, augmenting the GNN with informative node features substantially improves its performance on the MCP, increasing the median largest-found clique size by 22% (from 29.5 to 36) on large graphs from the BHOSLIB-DIMACS dataset.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 72 of its 144 references that are in the map. First posted on arXiv 28 Nov 2025.
Builds on
72 of 144 references.
References · 72
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
- 2020Parameterized Explainer for Graph Neural Networkcited by 426
- 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
- 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
- 2022Discovering Invariant Rationales for Graph Neural Networkscited by 188
- 2022Interpretable and Generalizable Graph Learning via Stochastic Attention Mechanismcited by 171
- 2019Explainability Techniques for Graph Convolutional Networkscited by 161
- 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
- 2020Higher-Order Explanations of Graph Neural Networks via Relevant Walkscited by 138
38 more
- 2021Generative Causal Explanations for Graph Neural Networkscited by 124
- 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
- 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 119
- 2020Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphscited by 115
- 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
- 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 79
- 2021Towards Self-Explainable Graph Neural Networkcited by 75
- 2021Robust Counterfactual Explanations on Graph Neural Networkscited by 72
- 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 65
- 2021GraphSVX: Shapley Value Explanations for Graph Neural Networkscited by 64
- 2022Interpretable Graph Neural Networks for Connectome-Based Brain Disorder Analysiscited by 59
- 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 58
- 2020RelEx: A Model-Agnostic Relational Model Explainercited by 53
- 2022KerGNNs: Interpretable Graph Neural Networks with Graph Kernelscited by 50
- 2018Geometric Scattering for Graph Data Analysiscited by 49
- 2022CLEAR: Generative Counterfactual Explanations on Graphscited by 48
- 2018Graph Convolutional Neural Networks via Scatteringcited by 46
- 2021Improving Subgraph Recognition with Variational Graph Information Bottleneckcited by 45
- 2018Diffusion Scattering Transforms on Graphscited by 44
- 2022GStarX: Explaining Graph Neural Networks with Structure-Aware Cooperative Gamescited by 42
- 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
- 2021MEG: Generating Molecular Counterfactual Explanations for Deep Graph Networkscited by 32
- 2023A Survey on Explainability of Graph Neural Networkscited by 29
- 2023DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networkscited by 27
- 2022Can Hybrid Geometric Scattering Networks Help Solve the Maximum Clique Problem?cited by 25
- 2021Efficient and Interpretable Robot Manipulation with Graph Neural Networkscited by 22
- 2022GREASE: Generate Factual and Counterfactual Explanations for GNN-based Recommendationscited by 22
- 2023Variational Annealing on Graphs for Combinatorial Optimizationcited by 21
- 2021Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsitycited by 20
- 2021Online Multi-Agent Forecasting with Interpretable Collaborative Graph Neural Networkcited by 20
- 2023Explainable Brain Age Prediction using coVariance Neural Networkscited by 20
- 2023Multiscale Graph Neural Network Autoencoders for Interpretable Scientific Machine Learningcited by 18
- 2023Distill n' Explain: explaining graph neural networks using simple surrogatescited by 18
- 2023DEGREE: Decomposition Based Explanation For Graph Neural Networkscited by 18
- 2024Aligning Human Knowledge with Visual Concepts Towards Explainable Medical Image Classificationcited by 18
- 2022EchoGNN: Explainable Ejection Fraction Estimation with Graph Neural Networkscited by 17
- 2023CI-GNN: A Granger Causality-Inspired Graph Neural Network for Interpretable Brain Network-Based Psychiatric Diagnosiscited by 16
50 most cited of 72 All 72 (JSON)
Built on by
Not cited yet.