THeGAU: Type-Aware Heterogeneous Graph Autoencoder and Augmentation

TL;DR

THeGAU is a versatile framework that enhances heterogeneous graph neural networks by preserving type semantics and refining noisy structures, leading to improved accuracy and efficiency in node classification tasks.

Contribution

It introduces a type-aware autoencoder combined with guided augmentation, addressing information loss and structural noise in HGNNs, and achieves state-of-the-art results.

Findings

Outperforms existing HGNN methods on benchmark datasets

Improves robustness and accuracy in node classification

Reduces computational overhead significantly

Abstract

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.