提出无需训练的异构图压缩方法，显著降低计算开销同时保持精度。
HGC-Herd: Efficient Heterogeneous Graph Condensation via Representative Node Herding
- 基于类别感知的代表性节点选择机制，实现高效压缩
- 在ACM、DBLP等数据集上达到与全图训练相当的准确率
- 适合大规模异构图场景下的快速模型训练与部署
异构图神经网络在建模多类型节点与关系的复杂语义方面表现优异，但其在大规模图上的可扩展性仍受限于结构冗余和高维节点特征。现有图压缩方法（如GCond）主要针对同质图设计，依赖梯度匹配，带来显著的计算、内存和优化开销。我们提出HGC-Herd，一种无需训练的压缩框架，能够在保持语义与结构保真度的前提下生成紧凑且信息丰富的异构图。该方法引入轻量级特征传播以编码多跳关系上下文，并采用类别感知的聚类提取机制，为每类节点选取代表性子集，从而生成平衡且具有判别性的子图用于下游学习任务。在ACM、DBLP和Freebase上的实验表明，HGC-Herd在保持或超越全图训练精度的同时，显著降低了运行时间和内存消耗。结果凸显了其在高效、可扩展异构图表征学习中的实用价值。
原文摘要 · Abstract (English)
Heterogeneous graph neural networks (HGNNs) have demonstrated strong capability in modeling complex semantics across multi-type nodes and relations. However, their scalability to large-scale graphs remains challenging due to structural redundancy and high-dimensional node features. Existing graph condensation approaches, such as GCond, are primarily developed for homogeneous graphs and rely on gradient matching, resulting in considerable computational, memory, and optimization overhead. We propose HGC-Herd, a training-free condensation framework that generates compact yet informative heterogeneous graphs while maintaining both semantic and structural fidelity. HGC-Herd integrates lightweight feature propagation to encode multi-hop relational context and employs a class-wise herding mechanism to identify representative nodes per class, producing balanced and discriminative subsets for downstream learning tasks. Extensive experiments on ACM, DBLP, and Freebase validate that HGC-Herd attains comparable or superior accuracy to full-graph training while markedly reducing both runtime and memory consumption. These results underscore its practical value for efficient and scalable heterogeneous graph representation learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。