MHNF: Multi-hop Heterogeneous Neighborhood information Fusion graph representation learning

TL;DR

This paper introduces MHNF, a novel graph representation learning method that effectively aggregates multihop heterogeneous neighborhood information using hybrid metapaths and hierarchical semantic attention, outperforming existing models.

Contribution

The paper proposes a hybrid metapath autonomous extraction model, a hop-level heterogeneous aggregation model, and a hierarchical semantic attention fusion model for multihop heterogeneous graph learning.

Findings

Achieves state-of-the-art or competitive performance on real datasets.

Uses significantly fewer parameters and computational resources.

Effectively integrates multilevel semantic information.

Abstract

The attention mechanism enables graph neural networks (GNNs) to learn the attention weights between the target node and its one-hop neighbors, thereby improving the performance further. However, most existing GNNs are oriented toward homogeneous graphs, and in which each layer can only aggregate the information of one-hop neighbors. Stacking multilayer networks introduces considerable noise and easily leads to over smoothing. We propose here a multihop heterogeneous neighborhood information fusion graph representation learning method (MHNF). Specifically, we propose a hybrid metapath autonomous extraction model to efficiently extract multihop hybrid neighbors. Then, we formulate a hop-level heterogeneous information aggregation model, which selectively aggregates different-hop neighborhood information within the same hybrid metapath. Finally, a hierarchical semantic attention fusion model (HSAF) is constructed, which can efficiently integrate different-hop and different-path neighborhood information. In this fashion, this paper solves the problem of aggregating multihop neighborhood information and learning hybrid metapaths for target tasks. This mitigates the limitation of manually specifying metapaths. In addition, HSAF can extract the internal node information of the metapaths and better integrate the semantic information present at different levels. Experimental results on real datasets show that MHNF achieves the best or competitive performance against state-of-the-art baselines with only a fraction of 1/10 ~ 1/100 parameters and computational budgets. Our code is publicly available at https://github.com/PHD-lanyu/MHNF.