Heterogeneous Graph Condensation via Role-Aware Clustering

• URL: http://arxiv.org/abs/2607.03097v1
• Date: Fri, 03 Jul 2026 08:34:11 GMT
• Title: Heterogeneous Graph Condensation via Role-Aware Clustering
• Abstract summary: We propose HGC-RC, a simple yet effective role-aware heterogeneous graph condensation framework.<n> Specifically, HGC-RC first extracts semantically enhanced node embeddings via lightweight propagation.<n>It then introduces a role-aware hybrid clustering strategy to preserve class distributions and unsupervised type-wise clustering for non-target nodes.
• Score: 22.24436628820291
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Heterogeneous Graph Neural Networks (HGNNs) have exhibited remarkable efficacy in modeling complex systems with multiple types of nodes and relations, yet their training on large-scale heterogeneous graphs remains computationally prohibitive. Although graph condensation methods can effectively improve learning efficiency on large-scale graphs, existing condensation processes are mainly designed for homogeneous graphs and typically rely on computationally expensive gradient matching or bilevel optimization paradigms, rendering them impractical for heterogeneous settings. To address these limitations, we propose HGC-RC, a simple yet effective role-aware heterogeneous graph condensation framework. Specifically, HGC-RC first extracts semantically enhanced node embeddings via lightweight propagation. It then introduces a role-aware hybrid clustering strategy consisting of class-partitioned clustering for labeled target nodes to preserve class distributions and unsupervised type-wise clustering for non-target nodes to retain critical cross-type connectivity. Finally, a compact heterogeneous graph is efficiently reconstructed based on the resulting cluster assignments. Extensive experiments demonstrate that HGC-RC outperforms state-of-the-art baselines, offering a practical pathway to accelerate HGNN training on large-scale heterogeneous graphs without sacrificing task performance

Related papers

• An Efficient and Scalable Graph Condensation with Structure-Preserving [22.24436628820291]
  Graph condensation (GC) is pivotal for enabling Graph Neural Networks (GNNs) deployment in resource-constrained scenarios.<n>Existing GC methods commonly suffer from computational inefficiency due to coupled optimization as well as encountering poor generalization across GNN architectures.<n>This study proposes an Efficient and scalable Graph Condensation with Structure-Preserving (SP-ESGC) that separates node condensation from graph structure generation.
  arXiv  Detail & Related papers  (2026-05-29T08:49:17Z)
• HGC-Herd: Efficient Heterogeneous Graph Condensation via Representative Node Herding [17.632566656960673]
  Heterogeneous graph neural networks (HGNNs) have demonstrated strong capability in modeling complex semantics across multi-type nodes and relations.<n>We propose HGC-Herd, a training-free condensation framework that generates compact yet informative heterogeneous graphs.<n> Extensive experiments on ACM, DBLP, and Freebase validate that HGC-Herd attains comparable or superior accuracy to full-graph training.
  arXiv  Detail & Related papers  (2025-12-08T09:24:48Z)
• Towards Pre-trained Graph Condensation via Optimal Transport [52.6504753271008]
  Graph condensation aims to distill the original graph into a small-scale graph, mitigating redundancy and accelerating GNN training.<n> conventional GC approaches heavily rely on rigid GNNs and task-specific supervision.<n>Pre-trained Graph Condensation (PreGC) via optimal transport is proposed to transcend the limitations of task- and architecture-dependent GC methods.
  arXiv  Detail & Related papers  (2025-09-18T08:13:24Z)
• Simple yet Effective Graph Distillation via Clustering [2.6217304977339473]
  graph data distillation (GDD) seeks to distill large graphs into compact and informative ones.<n>ClustGDD synthesizes the condensed graph and node attributes through fast and theoretically-grounded clustering.<n>ClustGDD consistently achieve superior or comparable performance to state-of-the-art GDD methods in terms of node classification.
  arXiv  Detail & Related papers  (2025-05-27T07:13:10Z)
• Adaptive Homophily Clustering: Structure Homophily Graph Learning with Adaptive Filter for Hyperspectral Image [21.709368882043897]
  Hyperspectral image (HSI) clustering has been a fundamental but challenging task with zero training labels.<n>In this paper, a homophily structure graph learning with an adaptive filter clustering method (AHSGC) for HSI is proposed.<n>Our AHSGC contains high clustering accuracy, low computational complexity, and strong robustness.
  arXiv  Detail & Related papers  (2025-01-03T01:54:16Z)
• Graph Structure Refinement with Energy-based Contrastive Learning [56.957793274727514]
  We introduce an unsupervised method based on a joint of generative training and discriminative training to learn graph structure and representation.<n>We propose an Energy-based Contrastive Learning (ECL) guided Graph Structure Refinement (GSR) framework, denoted as ECL-GSR.<n>ECL-GSR achieves faster training with fewer samples and memories against the leading baseline, highlighting its simplicity and efficiency in downstream tasks.
  arXiv  Detail & Related papers  (2024-12-20T04:05:09Z)
• Training-free Heterogeneous Graph Condensation via Data Selection [74.06562124781104]
  We present the first Training underlineFree Heterogeneous Graph Condensation method, termed FreeHGC, facilitating both efficient and high-quality generation of heterogeneous condensed graphs.<n>Specifically, we reformulate the heterogeneous graph condensation problem as a data selection issue, offering a new perspective for assessing and condensing representative nodes and edges in the heterogeneous graphs.
  arXiv  Detail & Related papers  (2024-12-20T02:49:32Z)
• Rethinking and Accelerating Graph Condensation: A Training-Free Approach with Class Partition [49.41718583061147]
  Graph condensation is a data-centric solution to replace the large graph with a small yet informative condensed graph.<n>Existing GC methods suffer from intricate optimization processes, necessitating excessive computing resources and training time.<n>We propose a training-free GC framework termed Class-partitioned Graph Condensation (CGC)<n>CGC condenses the Ogbn-products graph within 30 seconds, achieving a speedup ranging from $102$X to $104$X and increasing accuracy by up to 4.2%.
  arXiv  Detail & Related papers  (2024-05-22T14:57:09Z)
• Efficient Heterogeneous Graph Learning via Random Projection [58.4138636866903]
  Heterogeneous Graph Neural Networks (HGNNs) are powerful tools for deep learning on heterogeneous graphs. Recent pre-computation-based HGNNs use one-time message passing to transform a heterogeneous graph into regular-shaped tensors. We propose a hybrid pre-computation-based HGNN, named Random Projection Heterogeneous Graph Neural Network (RpHGNN)
  arXiv  Detail & Related papers  (2023-10-23T01:25:44Z)
• Spatial-Spectral Clustering with Anchor Graph for Hyperspectral Image [88.60285937702304]
  This paper proposes a novel unsupervised approach called spatial-spectral clustering with anchor graph (SSCAG) for HSI data clustering. The proposed SSCAG is competitive against the state-of-the-art approaches.
  arXiv  Detail & Related papers  (2021-04-24T08:09:27Z)

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.