mlsanityData to 14 Oct 2026

DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networks

arXiv 2303.02448 ↗First posted 4 Mar 2023cs.LG cs.AIcited by 27

Not on the map. Why?

Abstract (arXiv)

Uncovering rationales behind predictions of graph neural networks (GNNs) has received increasing attention over the years. Existing literature mainly focus on selecting a subgraph, through combinatorial optimization, to provide faithful explanations. However, the exponential size of candidate subgraphs limits the applicability of state-of-the-art methods to large-scale GNNs. We enhance on this through a different approach: by proposing a generative structure -- GFlowNets-based GNN Explainer (GFlowExplainer), we turn the optimization problem into a step-by-step generative problem. Our GFlowExplainer aims to learn a policy that generates a distribution of subgraphs for which the probability of a subgraph is proportional to its' reward. The proposed approach eliminates the influence of node sequence and thus does not need any pre-training strategies. We also propose a new cut vertex matrix to efficiently explore parent states for GFlowNets structure, thus making our approach applicable in a large-scale setting. We conduct extensive experiments on both synthetic and real datasets, and both qualitative and quantitative results show the superiority of our GFlowExplainer.

Key facts. Cited by 27 papers in the map (data through 14 Oct 2026). Builds on 29 of its 40 references that are in the map. First posted on arXiv 4 Mar 2023.

Builds on

29 of 40 references.

References · 29

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Graph Attention Networkscited by 8,923
  3. 2017Inductive Representation Learning on Large Graphscited by 6,320
  4. 2018How Powerful are Graph Neural Networks?cited by 4,393
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  6. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  7. 2019Simplifying Graph Convolutional Networkscited by 1,477
  8. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  9. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  10. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  11. 2018Deep Learning on Graphs: A Surveycited by 393
  12. 2021Flow Network based Generative Models for Non-Iterative Diverse Candidate Generationcited by 392
17 more
  1. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
  2. 2020Towards Deeper Graph Neural Networkscited by 296
  3. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  4. 2022Trajectory balance: Improved credit assignment in GFlowNetscited by 251
  5. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  6. 2015Order Matters: Sequence to sequence for setscited by 237
  7. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  8. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 211
  9. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  10. 2022Biological Sequence Design with GFlowNetscited by 174
  11. 2019Explainability Techniques for Graph Convolutional Networkscited by 161
  12. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
  13. 2022Bayesian Structure Learning with Generative Flow Networkscited by 153
  14. 2020Higher-Order Explanations of Graph Neural Networks via Relevant Walkscited by 138
  15. 2022Generative Flow Networks for Discrete Probabilistic Modelingcited by 114
  16. 2021GraphSVX: Shapley Value Explanations for Graph Neural Networkscited by 64
  17. 2022GFlowCausal: Generative Flow Networks for Causal Discoverycited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 13; 2024: 7; 2025: 6; 2026: 1.

27 papers.

Sort:

By area:

  1. 2023Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimizationcited by 57
  2. 2023Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNetscited by 40
  3. 2024Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examplescited by 30
  4. 2023A Survey on Explainability of Graph Neural Networkscited by 29
  5. 2023TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discoverycited by 27
  6. 2025GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networkscited by 15
  7. 2024Explaining Graph Neural Networks via Structure-aware Interaction Indexcited by 11
  8. 2023D4Explainer: In-Distribution GNN Explanations via Discrete Denoising Diffusioncited by 9
  9. 2024Graph Neural Network Causal Explanation via Neural Causal Modelscited by 9
  10. 2023Generalized Universal Domain Adaptation with Generative Flow Networkscited by 7
  11. 2023Expected flow networks in stochastic environments and two-player zero-sum gamescited by 7
  12. 2023GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networkscited by 7
15 more
  1. 2025Recent Advances in Malware Detection: Graph Learning and Explainabilitycited by 7
  2. 2024EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Timecited by 5
  3. 2023Generative Explanations for Graph Neural Network: Methods and Evaluationscited by 4
  4. 2023Generative Flow Networks for Precise Reward-Oriented Active Learning on Graphscited by 3
  5. 2023GFlowNets with Human Feedbackcited by 3
  6. 2023ConfusionPrompt: Practical Private Inference for Online Large Language Modelscited by 3
  7. 2024Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networkscited by 3
  8. 2024xAI-Drop: Don't Use What You Cannot Explaincited by 3
  9. 2023Unstructured and structured data: Can we have the best of both worlds with large language models?cited by 2
  10. 2024CoDy: Counterfactual Explainers for Dynamic Graphscited by 2
  11. 2025Learning Decision Trees as Amortized Structure Inferencecited by 2
  12. 2025GnnXemplar: Exemplars to Explanations -- Natural Language Rules for Global GNN Interpretabilitycited by 2
  13. 2025Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependenciescited by 1
  14. 2025ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule miningcited by 0
  15. 2026CounterFlowNet: From Minimal Changes to Meaningful Counterfactual Explanationscited by 0