THeGAU: Type-Aware Heterogeneous Graph Autoencoder and Augmentation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hong, Ming-Yi, Chiang, Miao-Chen, Teng, Youchen, Wang, Yu-Hsiang, Wang, Chih-Yu, Lin, Che
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918244263133184
author Hong, Ming-Yi
Chiang, Miao-Chen
Teng, Youchen
Wang, Yu-Hsiang
Wang, Chih-Yu
Lin, Che
author_facet Hong, Ming-Yi
Chiang, Miao-Chen
Teng, Youchen
Wang, Yu-Hsiang
Wang, Chih-Yu
Lin, Che
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_10589
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle THeGAU: Type-Aware Heterogeneous Graph Autoencoder and Augmentation
Hong, Ming-Yi
Chiang, Miao-Chen
Teng, Youchen
Wang, Yu-Hsiang
Wang, Chih-Yu
Lin, Che
Machine Learning
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.
title THeGAU: Type-Aware Heterogeneous Graph Autoencoder and Augmentation
topic Machine Learning
url https://arxiv.org/abs/2512.10589