mlsanityData to 7 Oct 2026

The Interpretable and Effective Graph Neural Additive Networks

arXiv 2406.01317 ↗First posted 3 Jun 2024cs.LG cs.AIcited by 19

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have emerged as the predominant approach for learning over graph-structured data. However, most GNNs operate as black-box models and require post-hoc explanations, which may not suffice in high-stakes scenarios where transparency is crucial. In this paper, we present a GNN that is interpretable by design. Our model, Graph Neural Additive Network (GNAN), is a novel extension of the interpretable class of Generalized Additive Models, and can be visualized and fully understood by humans. GNAN is designed to be fully interpretable, offering both global and local explanations at the feature and graph levels through direct visualization of the model. These visualizations describe exactly how the model uses the relationships between the target variable, the features, and the graph. We demonstrate the intelligibility of GNANs in a series of examples on different tasks and datasets. In addition, we show that the accuracy of GNAN is on par with black-box GNNs, making it suitable for critical applications where transparency is essential, alongside high accuracy.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 35 of its 68 references that are in the map. First posted on arXiv 3 Jun 2024.

Builds on

35 of 68 references.

References · 35

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  6. 2018How Powerful are Graph Neural Networks?cited by 4,355
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  8. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  9. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  10. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,571
  11. 2019Simplifying Graph Convolutional Networkscited by 1,470
  12. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
23 more
  1. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
  2. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  3. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  4. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  5. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 624
  6. 2020Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classificationcited by 500
  7. 2020Parameterized Explainer for Graph Neural Networkcited by 423
  8. 2020Graph Structure Learning for Robust Graph Neural Networkscited by 368
  9. 2016European Union regulations on algorithmic decision-making and a "right to explanation"cited by 343
  10. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 332
  11. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 318
  12. 2021Do Transformers Really Perform Bad for Graph Representation?cited by 318
  13. 2020SIGN: Scalable Inception Graph Neural Networkscited by 283
  14. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  15. 2020Machine Learning on Graphs: A Model and Comprehensive Taxonomycited by 156
  16. 2024Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spacescited by 132
  17. 2021Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunitiescited by 125
  18. 2020Graph Information Bottleneck for Subgraph Recognitioncited by 119
  19. 2022Impossibility Theorems for Feature Attributioncited by 78
  20. 2021Improving Graph Neural Networks with Simple Architecture Designcited by 41
  21. 2023Graph Neural Networks Use Graphs When They Shouldn'tcited by 25
  22. 2023Optimality of Message-Passing Architectures for Sparse Graphscited by 13
  23. 2022TREE-G: Decision Trees Contesting Graph Neural Networkscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 11; 2026: 7.

19 papers.

Sort:

  1. 2025Beyond Topological Self-Explainable GNNs: A Formal Explainability Perspectivecited by 10
  2. 2025Structured Spectral Graph Representation Learning for Multi-label Abnormality Analysis from 3D CT Scanscited by 3
  3. 2025Additive Models Explained: A Computational Complexity Approachcited by 3
  4. 2026GNN Explanations that do not Explain and How to find Themcited by 3
  5. 2026Graph Tokenization for Bridging Graphs and Transformerscited by 3
  6. 2025Structured Spectral Graph Learning for Anomaly Classification in 3D Chest CT Scanscited by 2
  7. 2024On the Utilization of Unique Node Identifiers in Graph Neural Networkscited by 1
  8. 2025GEDAN: Learning the Edit Costs for Graph Edit Distancecited by 1
  9. 2026Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learningcited by 1
  10. 2026Provably Explaining Neural Additive Modelscited by 1
  11. 2025Graph Attention Networks Unleashed: A Fast and Explainable Vulnerability Assessment Framework for Microgridscited by 0
  12. 2025Identifying Critical Phases for Disease Onset with Sparse Haematological Biomarkerscited by 0
7 more
  1. 2025Heterogeneous networks in drug-target interaction predictioncited by 0
  2. 2025SuperMAN: Interpretable and Expressive Networks over Temporally Sparse Heterogeneous Datacited by 0
  3. 2025The Architecture of Trust: A Framework for AI-Augmented Real Estate Valuation in the Era of Structured Datacited by 0
  4. 2025Graph Mixing Additive Networkscited by 0
  5. 2026Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learningcited by 0
  6. 2026Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMscited by 0
  7. 2026MolLedger: An Additive Graph Neural Network with Chemically Grounded ADME Attributionscited by 0