HeterSEED: Semantics-Structure Decoupling for Heterogeneous Graph Learning under Heterophily

• URL: http://arxiv.org/abs/2605.04594v1
• Date: Wed, 06 May 2026 07:42:22 GMT
• Title: HeterSEED: Semantics-Structure Decoupling for Heterogeneous Graph Learning under Heterophily
• Abstract summary: HeterSEED is a semantics-structure decoupling framework for heterogeneous graph learning under heterophily.<n>HeterSEED decouples representation learning into a heterogeneous semantic channel that captures type- and relation-aware local semantics.<n>A node-level adaptive fusion mechanism then combines the two channels to produce context-dependent node representations.
• Score: 38.14849479041363
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many real-world heterogeneous graphs exhibit pronounced heterophily, where connected nodes often have dissimilar labels or play different semantic roles. In such settings, standard heterogeneous graph neural networks that aggregate messages along metapaths or meta-relations primarily based on feature similarity can propagate misleading information, since feature similarity may be misaligned with underlying relational semantics. In this paper, we propose HeterSEED, a semantics-structure decoupling framework for heterogeneous graph learning under heterophily. HeterSEED decouples representation learning into a heterogeneous semantic channel that captures type- and relation-aware local semantics and a structure-aware heterophily channel that separates homophilic and heterophilic neighborhoods via pseudo-label-guided partitioning and aggregates them using metapath-based structural weights. A node-level adaptive fusion mechanism then combines the two channels to produce context-dependent node representations. Theoretically, we establish that, on heterogeneous graphs under heterophily, HeterSEED is strictly more expressive than standard heterogeneous graph neural networks that rely primarily on feature similarity and provably reduces the prediction bias introduced by heterophilic neighbors. Experiments on five real-world heterogeneous graphs, including two large-scale networks at the million-node and hundred-million-edge scale, demonstrate that HeterSEED consistently outperforms representative heterogeneous graph neural networks and recent heterophily-aware baselines, especially in strongly heterophilic regimes.

Related papers

• Adaptive Heterogeneous Graph Neural Networks: Bridging Heterophily and Heterogeneity [20.67252453378065]
  Heterogeneous graphs (HGs) are common in real-world scenarios and often exhibit heterophily.<n>We propose the Adaptive Heterogeneous Graph Neural Network (AHGNN) to tackle these challenges.<n>AHGNN employs a heterophily-aware convolution that accounts for heterophily distributions specific to both hops and meta-paths.
  arXiv  Detail & Related papers  (2025-08-08T05:39:58Z)
• Enhancing Homophily-Heterophily Separation: Relation-Aware Learning in Heterogeneous Graphs [14.452589880736523]
  We propose Relation-Aware Separation of Homophily and Heterophily (RASH), a novel contrastive learning framework.<n>RASH explicitly models high-order semantics of heterogeneous interactions and adaptively separates homophilic and heterophilic patterns.<n>A multi-relation contrastive loss is designed to align heterogeneous and homophilic/heterophilic views by maximizing mutual information.
  arXiv  Detail & Related papers  (2025-06-26T03:54:06Z)
• The Heterophilic Graph Learning Handbook: Benchmarks, Models, Theoretical Analysis, Applications and Challenges [101.83124435649358]
  Homophily principle, ie nodes with the same labels or similar attributes are more likely to be connected. Recent work has identified a non-trivial set of datasets where GNN's performance compared to the NN's is not satisfactory.
  arXiv  Detail & Related papers  (2024-07-12T18:04:32Z)
• Hetero$^2$Net: Heterophily-aware Representation Learning on Heterogenerous Graphs [38.858702539146385]
  We present Hetero$2$Net, a heterophily-aware HGNN that incorporates both masked metapath prediction and masked label prediction tasks. We evaluate the performance of Hetero$2$Net on five real-world heterogeneous graph benchmarks with varying levels of heterophily.
  arXiv  Detail & Related papers  (2023-10-18T02:19:12Z)
• Histopathology Whole Slide Image Analysis with Heterogeneous Graph Representation Learning [78.49090351193269]
  We propose a novel graph-based framework to leverage the inter-relationships among different types of nuclei for WSI analysis. Specifically, we formulate the WSI as a heterogeneous graph with "nucleus-type" attribute to each node and a semantic attribute similarity to each edge. Our framework outperforms the state-of-the-art methods with considerable margins on various tasks.
  arXiv  Detail & Related papers  (2023-07-09T14:43:40Z)
• Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All? [61.35457647107439]
  Most real-world homophilic and heterophilic graphs are comprised of a mixture of nodes in both homophilic and heterophilic structural patterns. We provide evidence that Graph Neural Networks(GNNs) on node classification typically perform admirably on homophilic nodes. We then propose a rigorous, non-i.i.d PAC-Bayesian generalization bound for GNNs, revealing reasons for the performance disparity.
  arXiv  Detail & Related papers  (2023-06-02T07:46:20Z)
• Heterophily-Aware Graph Attention Network [42.640057865981156]
  Graph Neural Networks (GNNs) have shown remarkable success in graph representation learning. Existing heterophilic GNNs tend to ignore the modeling of heterophily of each edge, which is also a vital part in tackling the heterophily problem. We propose a novel Heterophily-Aware Graph Attention Network (HA-GAT) by fully exploring and utilizing the local distribution as the underlying heterophily.
  arXiv  Detail & Related papers  (2023-02-07T03:21:55Z)
• Simple and Efficient Heterogeneous Graph Neural Network [55.56564522532328]
  Heterogeneous graph neural networks (HGNNs) have powerful capability to embed rich structural and semantic information of a heterogeneous graph into node representations. Existing HGNNs inherit many mechanisms from graph neural networks (GNNs) over homogeneous graphs, especially the attention mechanism and the multi-layer structure. This paper conducts an in-depth and detailed study of these mechanisms and proposes Simple and Efficient Heterogeneous Graph Neural Network (SeHGNN)
  arXiv  Detail & Related papers  (2022-07-06T10:01:46Z)
• Heterogeneous Graph Neural Networks using Self-supervised Reciprocally Contrastive Learning [102.9138736545956]
  Heterogeneous graph neural network (HGNN) is a very popular technique for the modeling and analysis of heterogeneous graphs. We develop for the first time a novel and robust heterogeneous graph contrastive learning approach, namely HGCL, which introduces two views on respective guidance of node attributes and graph topologies. In this new approach, we adopt distinct but most suitable attribute and topology fusion mechanisms in the two views, which are conducive to mining relevant information in attributes and topologies separately.
  arXiv  Detail & Related papers  (2022-04-30T12:57:02Z)
• Powerful Graph Convolutioal Networks with Adaptive Propagation Mechanism for Homophily and Heterophily [38.50800951799888]
  Graph Convolutional Networks (GCNs) have been widely applied in various fields due to their significant power on processing graph-structured data. Existing methods deal with heterophily by mainly aggregating higher-order neighborhoods or combing the immediate representations. This paper proposes a novel propagation mechanism, which can automatically change the propagation and aggregation process according to homophily or heterophily.
  arXiv  Detail & Related papers  (2021-12-27T08:19:23Z)
• Learning on heterogeneous graphs using high-order relations [37.64632406923687]
  We propose an approach for learning on heterogeneous graphs without using meta-paths. We decompose a heterogeneous graph into different homogeneous relation-type graphs, which are then combined to create higher-order relation-type representations.
  arXiv  Detail & Related papers  (2021-03-29T12:02:47Z)

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.