LSPI: Heterogeneous Graph Neural Network Classification Aggregation Algorithm Based on Size Neighbor Path Identification

TL;DR

This paper introduces LSPI, a novel heterogeneous graph neural network algorithm that distinguishes between large and small neighbor paths to improve classification accuracy by reducing noise and enhancing feature aggregation.

Contribution

The paper proposes a new meta-path division and filtering approach in HGNNs, improving performance by reducing noise from large neighbor paths and using subgraph-level attention for feature fusion.

Findings

LSPI outperforms existing HGNN methods in experiments.

Filtering large neighbor paths improves classification accuracy.

Subgraph-level attention effectively fuses multi-scale features.

Abstract

Existing heterogeneous graph neural network algorithms (HGNNs) mostly rely on meta-paths to capture the rich semantic information contained in heterogeneous graphs (also known as heterogeneous information networks (HINs)), but most of these HGNNs focus on different ways of feature aggre gation and ignore the properties of the meta-paths themselves. This paper studies meta-paths in three commonly used data sets and finds that there are huge differences in the number of neighbors connected by different meta paths. At the same time, the noise information contained in large neigh bor paths will have an adverse impact on model performance. Therefore, this paper proposes a Heterogeneous Graph Neural Network Classification and Aggregation Algorithm Based on Large and Small Neighbor Path Iden tification(LSPI). LSPI firstly divides the meta-paths into large and small neighbor paths through the path discriminator , and in order to reduce the noise interference problem in large neighbor paths, LSPI selects neighbor nodes with higher similarity from both topology and feature perspectives, and passes small neighbor paths and filtered large neighbor paths through different graph convolution components. Aggregation is performed to obtain feature information under different subgraphs, and then LSPI uses subgraph level attention to fuse the feature information under different subgraphs to generate the final node embedding. Finally this paper verifies the superiority of the method through extensive experiments and also gives suggestions on the number of nodes to be retained in large neighbor paths through exper iments. The complete reproducible code adn data has been published at: https://github.com/liuhua811/LSPIA.