通过类型感知与引导增强，提升异构图神经网络的分类精度与鲁棒性。
THeGAU: Type-Aware Heterogeneous Graph Autoencoder and Augmentation
- 利用类型感知自编码器重建合法边，保留节点类型语义。
- 在三个基准数据集上超越现有方法，提升分类准确率。
- 适用于复杂异构网络建模，适合需要高泛化能力的研究者。
异构图神经网络（HGNNs）在建模异构信息网络（HINs）方面表现优异，可编码多类型实体与关系。然而，现有方法常面临类型信息丢失与结构噪声问题，限制了表征保真度与泛化能力。本文提出THeGAU，一种模型无关框架，结合类型感知图自编码器与引导式图增强机制，以提升节点分类性能。该框架通过重建符合模式的边作为辅助任务，保留节点类型语义，并引入解码器驱动的增强策略，有选择地优化噪声结构。该联合设计提升了模型鲁棒性、准确性与效率，同时显著降低计算开销。在IMDB、ACM和DBLP三个基准数据集上的大量实验表明，THeGAU在多种主干网络上均持续优于现有HGNN方法，达到当前最优性能。
原文摘要 · Abstract (English)
Heterogeneous Graph Neural Networks (HGNNs) are effective for modeling Heterogeneous Information Networks (HINs), which encode complex multi-typed entities and relations. However, HGNNs often suffer from type information loss and structural noise, limiting their representational fidelity and generalization. We propose THeGAU, a model-agnostic framework that combines a type-aware graph autoencoder with guided graph augmentation to improve node classification. THeGAU reconstructs schema-valid edges as an auxiliary task to preserve node-type semantics and introduces a decoder-driven augmentation mechanism to selectively refine noisy structures. This joint design enhances robustness, accuracy, and efficiency while significantly reducing computational overhead. Extensive experiments on three benchmark HIN datasets (IMDB, ACM, and DBLP) demonstrate that THeGAU consistently outperforms existing HGNN methods, achieving state-of-the-art performance across multiple backbones.
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。