IMPA-HGAE:Intra-Meta-Path Augmented Heterogeneous Graph Autoencoder

TL;DR

IMPA-HGAE introduces a novel self-supervised learning framework that fully exploits internal node information along meta-paths in heterogeneous graphs, improving embedding quality and interpretability.

Contribution

The paper proposes a new framework that enhances node embeddings by utilizing internal meta-path information and introduces masking strategies for better generative SSL on heterogeneous graphs.

Findings

Superior performance on heterogeneous datasets

Effective masking strategies for SSL models

Enhanced interpretability of graph embeddings

Abstract

Self-supervised learning (SSL) methods have been increasingly applied to diverse downstream tasks due to their superior generalization capabilities and low annotation costs. However, most existing heterogeneous graph SSL models convert heterogeneous graphs into homogeneous ones via meta-paths for training, which only leverage information from nodes at both ends of meta-paths while underutilizing the heterogeneous node information along the meta-paths. To address this limitation, this paper proposes a novel framework named IMPA-HGAE to enhance target node embeddings by fully exploiting internal node information along meta-paths. Experimental results validate that IMPA-HGAE achieves superior performance on heterogeneous datasets. Furthermore, this paper introduce innovative masking strategies to strengthen the representational capacity of generative SSL models on heterogeneous graph data. Additionally, this paper discuss the interpretability of the proposed method and potential future directions for generative self-supervised learning in heterogeneous graphs. This work provides insights into leveraging meta-path-guided structural semantics for robust representation learning in complex graph scenarios.