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

• URL: http://arxiv.org/abs/2509.09337v1
• Date: Thu, 11 Sep 2025 10:45:50 GMT
• Title: MoSE: Unveiling Structural Patterns in Graphs via Mixture of Subgraph Experts
• Abstract summary: Mixture of Subgraph Experts (MoSE) framework for flexible and expressive subgraph-based representation learning.<n>MoSE extracts informative subgraphs via anonymous walks and dynamically routes them to specialized experts based on structural semantics.
• Score: 16.73906351854299
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Integrating Structural and Semantic Signals in Text-Attributed Graphs with BiGTex [0.16385815610837165]
  BiGTex is a novel architecture that tightly integrates GNNs and LLMs through stacked Graph-Text Fusion Units.<n>BiGTex achieves state-of-the-art performance in node classification and generalizes effectively to link prediction.
  arXiv  Detail & Related papers  (2025-04-16T20:25:11Z)
• Revisiting Graph Neural Networks on Graph-level Tasks: Comprehensive Experiments, Analysis, and Improvements [54.006506479865344]
  We propose a unified evaluation framework for graph-level Graph Neural Networks (GNNs)<n>This framework provides a standardized setting to evaluate GNNs across diverse datasets.<n>We also propose a novel GNN model with enhanced expressivity and generalization capabilities.
  arXiv  Detail & Related papers  (2025-01-01T08:48:53Z)
• Motif-driven Subgraph Structure Learning for Graph Classification [25.205435425328215]
  Graph Structure Learning (GSL) has emerged as a promising approach to improve graph structure and boost performance in downstream tasks. We propose a novel Motif-driven Subgraph Structure Learning method for Graph Classification (MOSGSL)
  arXiv  Detail & Related papers  (2024-06-13T07:50:44Z)
• GraphEdit: Large Language Models for Graph Structure Learning [14.16155596597421]
  Graph Structure Learning (GSL) focuses on capturing intrinsic dependencies and interactions among nodes in graph-structured data.<n>Existing GSL methods heavily depend on explicit graph structural information as supervision signals.<n>We propose GraphEdit, an approach that leverages large language models (LLMs) to learn complex node relationships in graph-structured data.
  arXiv  Detail & Related papers  (2024-02-23T08:29:42Z)
• GraphGLOW: Universal and Generalizable Structure Learning for Graph Neural Networks [72.01829954658889]
  This paper introduces the mathematical definition of this novel problem setting. We devise a general framework that coordinates a single graph-shared structure learner and multiple graph-specific GNNs. The well-trained structure learner can directly produce adaptive structures for unseen target graphs without any fine-tuning.
  arXiv  Detail & Related papers  (2023-06-20T03:33:22Z)
• Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptive Residual Module [65.81781176362848]
  Graph Neural Networks (GNNs) can learn from graph-structured data through neighborhood information aggregation. As the number of layers increases, node representations become indistinguishable, which is known as over-smoothing. We propose a textbfPosterior-Sampling-based, Node-distinguish Residual module (PSNR).
  arXiv  Detail & Related papers  (2023-05-09T12:03:42Z)
• Combining Stochastic Explainers and Subgraph Neural Networks can Increase Expressivity and Interpretability [12.526174412246107]
  Subgraph-enhanced graph neural networks (SGNN) can increase the power of the standard message-passing framework. We introduce a novel framework that jointly predicts the class of the graph and a set of explanatory sparse subgraphs.
  arXiv  Detail & Related papers  (2023-04-14T14:21:20Z)
• Ordered Subgraph Aggregation Networks [19.18478955240166]
  Subgraph-enhanced graph neural networks (GNNs) have emerged, provably boosting the expressive power of standard (message-passing) GNNs. Here, we introduce a theoretical framework and extend the known expressivity results of subgraph-enhanced GNNs. We show that increasing subgraph size always increases the expressive power and develop a better understanding of their limitations.
  arXiv  Detail & Related papers  (2022-06-22T15:19:34Z)
• Hypergraph Convolutional Networks via Equivalency between Hypergraphs and Undirected Graphs [59.71134113268709]
  We present General Hypergraph Spectral Convolution(GHSC), a general learning framework that can handle EDVW and EIVW hypergraphs. In this paper, we show that the proposed framework can achieve state-of-the-art performance. Experiments from various domains including social network analysis, visual objective classification, protein learning demonstrate that the proposed framework can achieve state-of-the-art performance.
  arXiv  Detail & Related papers  (2022-03-31T10:46:47Z)
• Equivariant Subgraph Aggregation Networks [23.26140936226352]
  This paper proposes a novel framework called Equivariant Subgraph Aggregation Networks (ESAN) to address this issue. While two graphs may not be distinguishable by an MPNN, they often contain distinguishable subgraphs. We develop novel variants of the 1-dimensional Weisfeiler-Leman (1-WL) test for graph isomorphism, and prove lower bounds on the expressiveness of ESAN. We provide theoretical results that describe how design choices such as the subgraph selection policy and equivariant neural architecture affect our architecture's expressive power.
  arXiv  Detail & Related papers  (2021-10-06T16:45:07Z)
• Learning compositional structures for semantic graph parsing [81.41592892863979]
  We show how AM dependency parsing can be trained directly on a neural latent-variable model. Our model picks up on several linguistic phenomena on its own and achieves comparable accuracy to supervised training.
  arXiv  Detail & Related papers  (2021-06-08T14:20:07Z)
• Learning the Implicit Semantic Representation on Graph-Structured Data [57.670106959061634]
  Existing representation learning methods in graph convolutional networks are mainly designed by describing the neighborhood of each node as a perceptual whole. We propose a Semantic Graph Convolutional Networks (SGCN) that explores the implicit semantics by learning latent semantic-paths in graphs.
  arXiv  Detail & Related papers  (2021-01-16T16:18:43Z)
• Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting [63.04999833264299]
  "Graph Substructure Networks" (GSN) is a topologically-aware message passing scheme based on substructure encoding. We show that it is strictly more expressive than the Weisfeiler-Leman (WL) graph isomorphism test. We perform an extensive evaluation on graph classification and regression tasks and obtain state-of-the-art results in diverse real-world settings.
  arXiv  Detail & Related papers  (2020-06-16T15:30:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.