Schema-Aware Deep Graph Convolutional Networks for Heterogeneous Graphs

TL;DR

This paper introduces DHGCN, a schema-aware deep graph convolutional network for heterogeneous graphs that effectively captures multi-hop information while mitigating over-smoothing, leading to improved performance.

Contribution

The paper proposes a novel hierarchical GCN framework that leverages graph schema and metapaths to enhance message passing in heterogeneous graphs.

Findings

Demonstrates performance improvements over existing methods on real datasets.

Effectively captures multi-hop neighbor information without over-smoothing.

Validates design choices through experiments on synthetic and real data.

Abstract

Graph convolutional network (GCN) based approaches have achieved significant progress for solving complex, graph-structured problems. GCNs incorporate the graph structure information and the node (or edge) features through message passing and computes 'deep' node representations. Despite significant progress in the field, designing GCN architectures for heterogeneous graphs still remains an open challenge. Due to the schema of a heterogeneous graph, useful information may reside multiple hops away. A key question is how to perform message passing to incorporate information of neighbors multiple hops away while avoiding the well-known over-smoothing problem in GCNs. To address this question, we propose our GCN framework 'Deep Heterogeneous Graph Convolutional Network (DHGCN)', which takes advantage of the schema of a heterogeneous graph and uses a hierarchical approach to effectively utilize information many hops away. It first computes representations of the target nodes based on their 'schema-derived ego-network' (SEN). It then links the nodes of the same type with various pre-defined metapaths and performs message passing along these links to compute final node representations. Our design choices naturally capture the way a heterogeneous graph is generated from the schema. The experimental results on real and synthetic datasets corroborate the design choice and illustrate the performance gains relative to competing alternatives.