Attention-Driven Metapath Encoding in Heterogeneous Graphs

TL;DR

This paper introduces an attention-based encoding framework for metapaths in heterogeneous graphs, enhancing node classification by capturing semantic structures without dropping nodes, and demonstrates competitive results on IMDB dataset.

Contribution

It is the first to incorporate attention mechanisms into metapath encoding without node dropping, improving semantic relation extraction in heterogeneous graph learning.

Findings

Competitive performance on IMDB node classification benchmark

Effective encoding of semantic structures in heterogeneous graphs

Enhanced robustness and generality of the framework

Abstract

One of the emerging techniques in node classification in heterogeneous graphs is to restrict message aggregation to pre-defined, semantically meaningful structures called metapaths. This work is the first attempt to incorporate attention into the process of encoding entire metapaths without dropping intermediate nodes. In particular, we construct two encoders: the first uses sequential attention to extend the multi-hop message passing algorithm designed in \citet{magna} to the metapath setting, and the second incorporates direct attention to extract semantic relations in the metapath. The model then employs the intra-metapath and inter-metapath aggregation mechanisms of \citet{han}. We furthermore use the powerful training scheduler specialized for heterogeneous graphs that was developed in \citet{lts}, ensuring the model slowly learns how to classify the most difficult nodes. The result is a resilient, general-purpose framework for capturing semantic structures in heterogeneous graphs. In particular, we demonstrate that our model is competitive with state-of-the-art models on performing node classification on the IMDB dataset, a popular benchmark introduced in \citet{benchmark}.