HAGNN: Hybrid Aggregation for Heterogeneous Graph Neural Networks

TL;DR

HAGNN introduces a hybrid aggregation framework that combines meta-path-based and meta-path-free methods to fully utilize semantic information in heterogeneous graphs, improving performance on multiple tasks.

Contribution

The paper proposes HAGNN, a novel framework that integrates intra-type and inter-type aggregation for heterogeneous GNNs, utilizing a new fused meta-path graph structure.

Findings

HAGNN outperforms existing models on node classification.

HAGNN improves results on node clustering.

HAGNN enhances link prediction accuracy.

Abstract

Heterogeneous graph neural networks (GNNs) have been successful in handling heterogeneous graphs. In existing heterogeneous GNNs, meta-path plays an essential role. However, recent work pointed out that simple homogeneous graph model without meta-path can also achieve comparable results, which calls into question the necessity of meta-path. In this paper, we first present the intrinsic difference about meta-path-based and meta-path-free models, i.e., how to select neighbors for node aggregation. Then, we propose a novel framework to utilize the rich type semantic information in heterogeneous graphs comprehensively, namely HAGNN (Hybrid Aggregation for Heterogeneous GNNs). The core of HAGNN is to leverage the meta-path neighbors and the directly connected neighbors simultaneously for node aggregations. HAGNN divides the overall aggregation process into two phases: meta-path-based intra-type aggregation and meta-path-free inter-type aggregation. During the intra-type aggregation phase, we propose a new data structure called fused meta-path graph and perform structural semantic aware aggregation on it. Finally, we combine the embeddings generated by each phase. Compared with existing heterogeneous GNN models, HAGNN can take full advantage of the heterogeneity in heterogeneous graphs. Extensive experimental results on node classification, node clustering, and link prediction tasks show that HAGNN outperforms the existing modes, demonstrating the effectiveness of HAGNN.