mlsanityData to 7 Oct 2026

Logical Distillation of Graph Neural Networks

arXiv 2406.07126 ↗First posted 11 Jun 2024cs.LG cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

We present a logic based interpretable model for learning on graphs and an algorithm to distill this model from a Graph Neural Network (GNN). Recent results have shown connections between the expressivity of GNNs and the two-variable fragment of first-order logic with counting quantifiers (C2). We introduce a decision-tree based model which leverages an extension of C2 to distill interpretable logical classifiers from GNNs. We test our approach on multiple GNN architectures. The distilled models are interpretable, succinct, and attain similar accuracy to the underlying GNN. Furthermore, when the ground truth is expressible in C2, our approach outperforms the GNN.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 13 of its 37 references that are in the map. First posted on arXiv 11 Jun 2024.

Builds on

13 of 37 references.

References · 13

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2018How Powerful are Graph Neural Networks?cited by 4,355
  3. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  4. 2020XGNN: Towards Model-Level Explanations of Graph Neural Networkscited by 211
  5. 2020GraphNorm: A Principled Approach to Accelerating Graph Neural Network Trainingcited by 116
  6. 2021The Logic of Graph Neural Networkscited by 84
  7. 2018Deep Neural Decision Treescited by 72
  8. 2017Beyond Sparsity: Tree Regularization of Deep Models for Interpretabilitycited by 68
  9. 2022Global Explainability of GNNs via Logic Combination of Learned Conceptscited by 64
  10. 2021GLocalX -- From Local to Global Explanations of Black Box AI Modelscited by 48
  11. 2022Explaining the Explainers in Graph Neural Networks: a Comparative Studycited by 34
  12. 2023The Descriptive Complexity of Graph Neural Networkscited by 26
1 more
  1. 2019Enhancing Decision Tree based Interpretation of Deep Neural Networks through L1-Orthogonal Regularizationcited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 2.

6 papers.

  1. 2025Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspectivecited by 10
  2. 2026GNN Explanations that do not Explain and How to find Themcited by 3
  3. 2025Sound Logical Explanations for Mean Aggregation Graph Neural Networkscited by 1
  4. 2025WILTing Trees: Interpreting the Distance Between MPNN Embeddingscited by 0
  5. 2025Discrete Diffusion-Based Model-Level Explanation of Heterogeneous GNNs with Node Featurescited by 0
  6. 2026Overcoming Shortcut Learning in Graph Neural Networks through Active Explanation Guidancecited by 0