# DAG Matters! GFlowNets Enhanced Explainer For Graph Neural Networks

arXiv: https://arxiv.org/abs/2303.02448 · HTML: https://mlsanity.com/paper/2303.02448/

## 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 (most cited first, 29 of 29)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Neural Message Passing for Quantum Chemistry](https://mlsanity.com/paper/1704.01212/) (2017)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [GNNExplainer: Generating Explanations for Graph Neural Networks](https://mlsanity.com/paper/1903.03894/) (2019)
- [Parameterized Explainer for Graph Neural Network](https://mlsanity.com/paper/2011.04573/) (2020)
- [Deep Learning on Graphs: A Survey](https://mlsanity.com/paper/1812.04202/) (2018)
- [Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation](https://mlsanity.com/paper/2106.04399/) (2021)
- [Explainability in Graph Neural Networks: A Taxonomic Survey](https://mlsanity.com/paper/2012.15445/) (2020)
- [Towards Deeper Graph Neural Networks](https://mlsanity.com/paper/2007.09296/) (2020)
- [On Explainability of Graph Neural Networks via Subgraph Explorations](https://mlsanity.com/paper/2102.05152/) (2021)
- [Trajectory balance: Improved credit assignment in GFlowNets](https://mlsanity.com/paper/2201.13259/) (2022)
- [Deep Convolutional Networks on Graph-Structured Data](https://mlsanity.com/paper/1506.05163/) (2015)
- [Order Matters: Sequence to sequence for sets](https://mlsanity.com/paper/1511.06391/) (2015)
- [XGNN: Towards Model-Level Explanations of Graph Neural Networks](https://mlsanity.com/paper/2006.02587/) (2020)
- [PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2010.05788/) (2020)
- [GraphLIME: Local Interpretable Model Explanations for Graph Neural Networks](https://mlsanity.com/paper/2001.06216/) (2020)
- [Biological Sequence Design with GFlowNets](https://mlsanity.com/paper/2203.04115/) (2022)
- [Explainability Techniques for Graph Convolutional Networks](https://mlsanity.com/paper/1905.13686/) (2019)
- [Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking](https://mlsanity.com/paper/2010.00577/) (2020)
- [Bayesian Structure Learning with Generative Flow Networks](https://mlsanity.com/paper/2202.13903/) (2022)
- [Higher-Order Explanations of Graph Neural Networks via Relevant Walks](https://mlsanity.com/paper/2006.03589/) (2020)
- [Generative Flow Networks for Discrete Probabilistic Modeling](https://mlsanity.com/paper/2202.01361/) (2022)
- [GraphSVX: Shapley Value Explanations for Graph Neural Networks](https://mlsanity.com/paper/2104.10482/) (2021)
- [GFlowCausal: Generative Flow Networks for Causal Discovery](https://mlsanity.com/paper/2210.08185/) (2022)

## Built on by (most cited first, 27 of 27)

- [Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization](https://mlsanity.com/paper/2310.02679/) (2023)
- [Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets](https://mlsanity.com/paper/2305.17010/) (2023)
- [Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples](https://mlsanity.com/paper/2406.05673/) (2024)
- [A Survey on Explainability of Graph Neural Networks](https://mlsanity.com/paper/2306.01958/) (2023)
- [TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery](https://mlsanity.com/paper/2310.19324/) (2023)
- [GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks](https://mlsanity.com/paper/2503.06514/) (2025)
- [Explaining Graph Neural Networks via Structure-aware Interaction Index](https://mlsanity.com/paper/2405.14352/) (2024)
- [D4Explainer: In-Distribution GNN Explanations via Discrete Denoising Diffusion](https://mlsanity.com/paper/2310.19321/) (2023)
- [Graph Neural Network Causal Explanation via Neural Causal Models](https://mlsanity.com/paper/2407.09378/) (2024)
- [Generalized Universal Domain Adaptation with Generative Flow Networks](https://mlsanity.com/paper/2305.04466/) (2023)
- [Expected flow networks in stochastic environments and two-player zero-sum games](https://mlsanity.com/paper/2310.02779/) (2023)
- [GRAPES: Learning to Sample Graphs for Scalable Graph Neural Networks](https://mlsanity.com/paper/2310.03399/) (2023)
- [Recent Advances in Malware Detection: Graph Learning and Explainability](https://mlsanity.com/paper/2502.10556/) (2025)
- [EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Time](https://mlsanity.com/paper/2405.01762/) (2024)
- [Generative Explanations for Graph Neural Network: Methods and Evaluations](https://mlsanity.com/paper/2311.05764/) (2023)
- [Generative Flow Networks for Precise Reward-Oriented Active Learning on Graphs](https://mlsanity.com/paper/2304.11989/) (2023)
- [GFlowNets with Human Feedback](https://mlsanity.com/paper/2305.07036/) (2023)
- [ConfusionPrompt: Practical Private Inference for Online Large Language Models](https://mlsanity.com/paper/2401.00870/) (2023)
- [Generating In-Distribution Proxy Graphs for Explaining Graph Neural Networks](https://mlsanity.com/paper/2402.02036/) (2024)
- [xAI-Drop: Don't Use What You Cannot Explain](https://mlsanity.com/paper/2407.20067/) (2024)
- [Unstructured and structured data: Can we have the best of both worlds with large language models?](https://mlsanity.com/paper/2304.13010/) (2023)
- [CoDy: Counterfactual Explainers for Dynamic Graphs](https://mlsanity.com/paper/2403.16846/) (2024)
- [Learning Decision Trees as Amortized Structure Inference](https://mlsanity.com/paper/2503.06985/) (2025)
- [GnnXemplar: Exemplars to Explanations -- Natural Language Rules for Global GNN Interpretability](https://mlsanity.com/paper/2509.18376/) (2025)
- [Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependencies](https://mlsanity.com/paper/2508.11513/) (2025)
- [ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule mining](https://mlsanity.com/paper/2511.22866/) (2025)
- [CounterFlowNet: From Minimal Changes to Meaningful Counterfactual Explanations](https://mlsanity.com/paper/2602.17244/) (2026)

## 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.