mlsanityData to 14 Oct 2026

DT+GNN: A Fully Explainable Graph Neural Network using Decision Trees

arXiv 2205.13234 ↗First posted 26 May 2022cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

We propose the fully explainable Decision Tree Graph Neural Network (DT+GNN) architecture. In contrast to existing black-box GNNs and post-hoc explanation methods, the reasoning of DT+GNN can be inspected at every step. To achieve this, we first construct a differentiable GNN layer, which uses a categorical state space for nodes and messages. This allows us to convert the trained MLPs in the GNN into decision trees. These trees are pruned using our newly proposed method to ensure they are small and easy to interpret. We can also use the decision trees to compute traditional explanations. We demonstrate on both real-world datasets and synthetic GNN explainability benchmarks that this architecture works as well as traditional GNNs. Furthermore, we leverage the explainability of DT+GNNs to find interesting insights into many of these datasets, with some surprising results. We also provide an interactive web tool to inspect DT+GNN's decision making.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 35 of its 57 references that are in the map. First posted on arXiv 26 May 2022.

Builds on

35 of 57 references.

References · 35

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  3. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
  5. 2018How Powerful are Graph Neural Networks?cited by 4,393
  6. 2017Neural Message Passing for Quantum Chemistrycited by 3,487
  7. 2016Categorical Reparameterization with Gumbel-Softmaxcited by 2,739
  8. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,434
  9. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
  10. 2016The Concrete Distribution: A Continuous Relaxation of Discrete Random Variablescited by 1,148
  11. 2017MoleculeNet: A Benchmark for Molecular Machine Learningcited by 1,051
  12. 2021Revisiting Deep Learning Models for Tabular Datacited by 740
23 more
  1. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 737
  2. 2020Parameterized Explainer for Graph Neural Networkcited by 426
  3. 2020Explainability in Graph Neural Networks: A Taxonomic Surveycited by 384
  4. 2018Consistent Individualized Feature Attribution for Tree Ensemblescited by 285
  5. 2021On Explainability of Graph Neural Networks via Subgraph Explorationscited by 281
  6. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  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. 2020Combining Label Propagation and Simple Models Out-performs Graph Neural Networkscited by 202
  10. 2019What graph neural networks cannot learn: depth vs widthcited by 201
  11. 2019Explainability Techniques for Graph Convolutional Networkscited by 161
  12. 2020Rumor Detection on Social Media with Bi-Directional Graph Convolutional Networkscited by 153
  13. 2020Interpreting Graph Neural Networks for NLP With Differentiable Edge Maskingcited by 153
  14. 2021ProtGNN: Towards Self-Explaining Graph Neural Networkscited by 96
  15. 2021Towards Self-Explainable Graph Neural Networkcited by 75
  16. 2018Deep Neural Decision Treescited by 72
  17. 2017Beyond Sparsity: Tree Regularization of Deep Models for Interpretabilitycited by 68
  18. 2021GraphSVX: Shapley Value Explanations for Graph Neural Networkscited by 64
  19. 2019Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classificationcited by 39
  20. 2021Probing GNN Explainers: A Rigorous Theoretical and Empirical Analysis of GNN Explanation Methodscited by 36
  21. 2020Contrastive Graph Neural Network Explanationcited by 20
  22. 2019Enhancing Decision Tree based Interpretation of Deep Neural Networks through L1-Orthogonal Regularizationcited by 9
  23. 2021Demystifying Graph Neural Network Explanationscited by 2

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 1; 2024: 2.

6 papers.

  1. 2024A Logic for Reasoning About Aggregate-Combine Graph Neural Networkscited by 10
  2. 2022A Survey of Neural Treescited by 7
  3. 2022MEGAN: Multi-Explanation Graph Attention Networkcited by 7
  4. 2024Towards Few-shot Self-explaining Graph Neural Networkscited by 4
  5. 2022Scaffold-Based Multi-Objective Drug Candidate Optimizationcited by 0
  6. 2023A Modal Logic for Explaining some Graph Neural Networkscited by 0