mlsanityData to 7 Oct 2026

KerGNNs: Interpretable Graph Neural Networks with Graph Kernels

arXiv 2201.00491 ↗First posted 3 Jan 2022cs.LG cs.AIcited by 50

Not on the map. Why?

Abstract (arXiv)

Graph kernels are historically the most widely-used technique for graph classification tasks. However, these methods suffer from limited performance because of the hand-crafted combinatorial features of graphs. In recent years, graph neural networks (GNNs) have become the state-of-the-art method in downstream graph-related tasks due to their superior performance. Most GNNs are based on Message Passing Neural Network (MPNN) frameworks. However, recent studies show that MPNNs can not exceed the power of the Weisfeiler-Lehman (WL) algorithm in graph isomorphism test. To address the limitations of existing graph kernel and GNN methods, in this paper, we propose a novel GNN framework, termed textitKernel Graph Neural Networks (KerGNNs), which integrates graph kernels into the message passing process of GNNs. Inspired by convolution filters in convolutional neural networks (CNNs), KerGNNs adopt trainable hidden graphs as graph filters which are combined with subgraphs to update node embeddings using graph kernels. In addition, we show that MPNNs can be viewed as special cases of KerGNNs. We apply KerGNNs to multiple graph-related tasks and use cross-validation to make fair comparisons with benchmarks. We show that our method achieves competitive performance compared with existing state-of-the-art methods, demonstrating the potential to increase the representation ability of GNNs. We also show that the trained graph filters in KerGNNs can reveal the local graph structures of the dataset, which significantly improves the model interpretability compared with conventional GNN models.

Key facts. Cited by 50 papers in the map (data through 7 Oct 2026). Builds on 32 of its 53 references that are in the map. First posted on arXiv 3 Jan 2022.

Builds on

32 of 53 references.

References · 32

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2018How Powerful are Graph Neural Networks?cited by 4,355
  5. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  6. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  7. 2018Weisfeiler and Leman Go Neural: Higher-order Graph Neural Networkscited by 878
  8. 2018Representation Learning on Graphs with Jumping Knowledge Networkscited by 875
  9. 2020Simple and Deep Graph Convolutional Networkscited by 857
  10. 2018Link Prediction Based on Graph Neural Networkscited by 829
  11. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  12. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 786
20 more
  1. 2019GNNExplainer: Generating Explanations for Graph Neural Networkscited by 735
  2. 2020Directional Message Passing for Molecular Graphscited by 556
  3. 2019Multi-scale Attributed Node Embeddingcited by 543
  4. 2019MixHop: Higher-Order Graph Convolutional Architectures via Sparsified Neighborhood Mixingcited by 442
  5. 2019Provably Powerful Graph Networkscited by 385
  6. 2017Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphscited by 307
  7. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  8. 2019Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernelscited by 160
  9. 2019Explainability Techniques for Graph Convolutional Networkscited by 160
  10. 2019A Survey on Graph Kernelscited by 148
  11. 2014Propagation Kernelscited by 88
  12. 2019Approximation Ratios of Graph Neural Networks for Combinatorial Problemscited by 68
  13. 2018GraKeL: A Graph Kernel Library in Pythoncited by 54
  14. 2014Convolutional Kernel Networkscited by 47
  15. 2020Convolutional Kernel Networks for Graph-Structured Datacited by 38
  16. 2016End-to-End Kernel Learning with Supervised Convolutional Kernel Networkscited by 28
  17. 2020Graph Homomorphism Convolutioncited by 27
  18. 2017Deriving Neural Architectures from Sequence and Graph Kernelscited by 23
  19. 2018Pre-training Graph Neural Networks with Kernelscited by 8
  20. 2017Kernel Graph Convolutional Neural Networkscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 8; 2023: 10; 2024: 13; 2025: 13; 2026: 6.

50 papers.

Sort:

By area:

  1. 2022Trustworthy Graph Neural Networks: Aspects, Methods and Trendscited by 88
  2. 2023CoCo: A Coupled Contrastive Framework for Unsupervised Domain Adaptive Graph Classificationcited by 46
  3. 2023A Survey on Explainability of Graph Neural Networkscited by 28
  4. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  5. 2022Graph Neural Networks in Particle Physics: Implementations, Innovations, and Challengescited by 12
  6. 2023A Survey on Malware Detection with Graph Representation Learningcited by 11
  7. 2024Explaining Graph Neural Networks via Structure-aware Interaction Indexcited by 10
  8. 2022Motif-based Graph Representation Learning with Application to Chemical Moleculescited by 9
  9. 2022Kernel-based Substructure Exploration for Next POI Recommendationcited by 8
  10. 2024Unveiling Global Interactive Patterns across Graphs: Towards Interpretable Graph Neural Networkscited by 8
  11. 2024Urban Region Pre-training and Prompting: A Graph-based Approachcited by 8
  12. 2022L2XGNN: Learning to Explain Graph Neural Networkscited by 7
38 more
  1. 2025Recent Advances in Malware Detection: Graph Learning and Explainabilitycited by 6
  2. 2023Interpretable Graph Neural Networks for Tabular Datacited by 5
  3. 2023How Faithful are Self-Explainable GNNs?cited by 5
  4. 2024Descriptive Kernel Convolution Network with Improved Random Walk Kernelcited by 5
  5. 2022Incorporating Heterophily into Graph Neural Networks for Graph Classificationcited by 4
  6. 2025From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networkscited by 4
  7. 2025B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Datacited by 4
  8. 2023Unsupervised Neighborhood Propagation Kernel Layers for Semi-supervised Node Classificationcited by 3
  9. 2023Structure-Aware DropEdge Towards Deep Graph Convolutional Networkscited by 3
  10. 2025Prediction via Shapley Value Regressioncited by 3
  11. 2025MoSE: Unveiling Structural Patterns in Graphs via Mixture of Subgraph Expertscited by 3
  12. 2026The End of Reward Engineering: How LLMs Are Redefining Multi-Agent Coordinationcited by 3
  13. 2023Augment to Interpret: Unsupervised and Inherently Interpretable Graph Embeddingscited by 1
  14. 2023Self-supervision meets kernel graph neural models: From architecture to augmentationscited by 1
  15. 2024Learning Attributed Graphlets: Predictive Graph Mining by Graphlets with Trainable Attributecited by 1
  16. 2024Discovering robust biomarkers of psychiatric disorders from resting-state functional MRI via graph neural networks: A systematic reviewcited by 1
  17. 2024ENADPool: The Edge-Node Attention-based Differentiable Pooling for Graph Neural Networkscited by 1
  18. 2024Topology Reorganized Graph Contrastive Learning with Mitigating Semantic Driftcited by 1
  19. 2024Interpretable Graph Neural Networks for Heterogeneous Tabular Datacited by 1
  20. 2024Grothendieck Graph Neural Networks Framework: An Algebraic Platform for Crafting Topology-Aware GNNscited by 1
  21. 2025SliceGX: Layer-wise GNN Explanation with Model-slicingcited by 1
  22. 2026Beyond Message Passing: A Symbolic Alternative for Expressive and Interpretable Graph Learningcited by 1
  23. 2022GRAPHYP: A Scientific Knowledge Graph with Manifold Subnetworks of Communities. Detection of Scholarly Disputes in Adversarial Information Routescited by 0
  24. 2022Tuning the Geometry of Graph Neural Networkscited by 0
  25. 2023A Causal Disentangled Multi-Granularity Graph Classification Methodcited by 0
  26. 2024GNN-LoFI: a Novel Graph Neural Network through Localized Feature-based Histogram Intersectioncited by 0
  27. 2024AKBR: Learning Adaptive Kernel-based Representations for Graph Classificationcited by 0
  28. 2024A Review of Graph-Powered Data Quality Applications for IoT Monitoring Sensor Networkscited by 0
  29. 2025Personalized Layer Selection for Graph Neural Networkscited by 0
  30. 2025LGRPool: Hierarchical Graph Pooling Via Local-Global Regularisationcited by 0
  31. 2025Disentangled Graph Representation Based on Substructure-Aware Graph Optimal Matching Kernel Convolutional Networkscited by 0
  32. 2025Are Graph Attention Networks Able to Model Structural Information?cited by 0
  33. 2025Exact Subgraph Isomorphism Network with Mixed L0,2 Norm Constraint for Predictive Graph Miningcited by 0
  34. 2025ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule miningcited by 0
  35. 2026Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learningcited by 0
  36. 2026h-MINT: Modeling Pocket-Ligand Binding with Hierarchical Molecular Interaction Networkcited by 0
  37. 2026Why Self-Inconsistency Arises in GNN Explanations and How to Exploit Itcited by 0
  38. 2026AIMing for Standardised Explainability Evaluation in GNNs: A Framework and Case Study on Graph Kernel Networkscited by 0