mlsanityData to 7 Oct 2026

MoSE: Unveiling Structural Patterns in Graphs via Mixture of Subgraph Experts

arXiv 2509.09337 ↗First posted 11 Sep 2025cs.LG cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

While graph neural networks (GNNs) have achieved great success in learning from graph-structured data, their reliance on local, pairwise message passing restricts their ability to capture complex, high-order subgraph patterns. leading to insufficient structural expressiveness. Recent efforts have attempted to enhance structural expressiveness by integrating random walk kernels into GNNs. However, these methods are inherently designed for graph-level tasks, which limits their applicability to other downstream tasks such as node classification. Moreover, their fixed kernel configurations hinder the model's flexibility in capturing diverse subgraph structures. To address these limitations, this paper proposes a novel Mixture of Subgraph Experts (MoSE) framework for flexible and expressive subgraph-based representation learning across diverse graph tasks. Specifically, MoSE extracts informative subgraphs via anonymous walks and dynamically routes them to specialized experts based on structural semantics, enabling the model to capture diverse subgraph patterns with improved flexibility and interpretability. We further provide a theoretical analysis of MoSE's expressivity within the Subgraph Weisfeiler-Lehman (SWL) Test, proving that it is more powerful than SWL. Extensive experiments, together with visualizations of learned subgraph experts, demonstrate that MoSE not only outperforms competitive baselines but also provides interpretable insights into structural patterns learned by the model.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 26 of its 48 references that are in the map. First posted on arXiv 11 Sep 2025.

Builds on

26 of 48 references.

References · 26

  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. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  6. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  7. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  8. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
  9. 2019A Fair Comparison of Graph Neural Networks for Graph Classificationcited by 244
  10. 2020Can Graph Neural Networks Count Substructures?cited by 235
  11. 2021Are Graph Augmentations Necessary? Simple Graph Contrastive Learning for Recommendationcited by 173
  12. 2019Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernelscited by 160
14 more
  1. 2023A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Testscited by 64
  2. 2023Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modelingcited by 63
  3. 2020ASGN: An Active Semi-supervised Graph Neural Network for Molecular Property Predictioncited by 58
  4. 2022KerGNNs: Interpretable Graph Neural Networks with Graph Kernelscited by 50
  5. 2020Convolutional Kernel Networks for Graph-Structured Datacited by 38
  6. 2015Steps Toward Deep Kernel Methods from Infinite Neural Networkscited by 28
  7. 2016End-to-End Kernel Learning with Supervised Convolutional Kernel Networkscited by 28
  8. 2024GraphMoRE: Mitigating Topological Heterogeneity via Mixture of Riemannian Expertscited by 23
  9. 2021Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernelscited by 19
  10. 2022SCARA: Scalable Graph Neural Networks with Feature-Oriented Optimizationcited by 19
  11. 2024Graph Sparsification via Mixture of Graphscited by 17
  12. 2023Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehmancited by 13
  13. 2023SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregationcited by 10
  14. 2024Descriptive Kernel Convolution Network with Improved Random Walk Kernelcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 2.

3 papers.

  1. 2026The Post-GCN Decade Revisited: Curvature-Stratified Evaluation of Relational Learningcited by 3
  2. 2025Adaptive Graph Mixture of Residual Experts: Unsupervised Learning on Diverse Graphs with Heterogeneous Specializationcited by 0
  3. 2026Scalable Heterogeneous Graph Learning via Heterogeneous-aware Orthogonal Prototype Expertscited by 0