mlsanityData to 14 Oct 2026

DEGREE: Decomposition Based Explanation For Graph Neural Networks

arXiv 2305.12895 ↗First posted 22 May 2023cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) are gaining extensive attention for their application in graph data. However, the black-box nature of GNNs prevents users from understanding and trusting the models, thus hampering their applicability. Whereas explaining GNNs remains a challenge, most existing methods fall into approximation based and perturbation based approaches with suffer from faithfulness problems and unnatural artifacts, respectively. To tackle these problems, we propose DEGREE degree to provide a faithful explanation for GNN predictions. By decomposing the information generation and aggregation mechanism of GNNs, DEGREE allows tracking the contributions of specific components of the input graph to the final prediction. Based on this, we further design a subgraph level interpretation algorithm to reveal complex interactions between graph nodes that are overlooked by previous methods. The efficiency of our algorithm can be further improved by utilizing GNN characteristics. Finally, we conduct quantitative and qualitative experiments on synthetic and real-world datasets to demonstrate the effectiveness of DEGREE on node classification and graph classification tasks.

Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). Builds on 33 of its 40 references that are in the map. First posted on arXiv 22 May 2023.

Builds on

33 of 40 references.

References · 33

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2017Graph Attention Networkscited by 8,923
  4. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2017Axiomatic Attribution for Deep Networkscited by 3,384
  7. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  8. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  9. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  10. 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
  11. 2018Link Prediction Based on Graph Neural Networkscited by 832
  12. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
21 more
  1. 2019Graph Neural Networks for Social Recommendationcited by 714
  2. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  3. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  4. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  5. 2018Techniques for Interpretable Machine Learningcited by 238
  6. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  7. 2020PGM-Explainer: Probabilistic Graphical Model Explanations for Graph Neural Networkscited by 211
  8. 2020GraphLIME: Local Interpretable Model Explanations for Graph Neural Networkscited by 209
  9. 2019Explainability Techniques for Graph Convolutional Networkscited by 161
  10. 2018Explaining Image Classifiers by Counterfactual Generationcited by 144
  11. 2020Higher-Order Explanations of Graph Neural Networks via Relevant Walkscited by 138
  12. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 119
  13. 2019Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Datacited by 104
  14. 2021DIG: A Turnkey Library for Diving into Graph Deep Learning Researchcited by 76
  15. 2018Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMscited by 67
  16. 2018Hierarchical interpretations for neural network predictionscited by 66
  17. 2019Layerwise Relevance Visualization in Convolutional Text Graph Classifierscited by 32
  18. 2019Is a Single Vector Enough? Exploring Node Polysemy for Network Embeddingcited by 29
  19. 2017Automatic Rule Extraction from Long Short Term Memory Networkscited by 10
  20. 2020Adversarial Infidelity Learning for Model Interpretationcited by 9
  21. 2020RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Designcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 6; 2025: 5; 2026: 3.

18 papers.

Sort:

  1. 2023A Survey on Explainability of Graph Neural Networkscited by 29
  2. 2024Graph Neural Network Explanations are Fragilecited by 19
  3. 2024CausalFormer: An Interpretable Transformer for Temporal Causal Discoverycited by 17
  4. 2024Explaining Graph Neural Networks via Structure-aware Interaction Indexcited by 11
  5. 2024GOAt: Explaining Graph Neural Networks via Graph Output Attributioncited by 10
  6. 2024Graph Neural Network Causal Explanation via Neural Causal Modelscited by 9
  7. 2025Recent Advances in Malware Detection: Graph Learning and Explainabilitycited by 7
  8. 2023Efficient GNN Explanation via Learning Removal-based Attributioncited by 6
  9. 2024EiG-Search: Generating Edge-Induced Subgraphs for GNN Explanation in Linear Timecited by 5
  10. 2023SSL Framework for Causal Inconsistency between Structures and Representationscited by 2
  11. 2025GnnXemplar: Exemplars to Explanations -- Natural Language Rules for Global GNN Interpretabilitycited by 2
  12. 2023A Review and Roadmap of Deep Causal Model from Different Causal Structures and Representationscited by 1
6 more
  1. 2025Model-Level GNN Explanations via Rule-to-Graph Readout for Logit Reconstructioncited by 0
  2. 2025Interpretable graph-based models on multimodal biomedical data integration: A technical review and benchmarkingcited by 0
  3. 2025ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule miningcited by 0
  4. 2026BAED: a New Paradigm for Few-shot Graph Learning with Explanation in the Loopcited by 0
  5. 2026Measuring What Matters: A Unified Evaluation Framework for GNN Explainabilitycited by 0
  6. 2026Towards Faithful Graph Explanations with Synergistic Edge Effects via Granular Ballscited by 0