CHAT: Beyond Contrastive Graph Transformer for Link Prediction in Heterogeneous Networks

TL;DR

CHAT introduces a novel graph transformer approach that effectively predicts links in complex heterogeneous networks without relying on predefined meta-paths, overcoming over-smoothing issues and improving accuracy.

Contribution

The paper presents CHAT, a new sampling-based graph transformer that encodes node sequences with high fidelity and enhances link prediction in heterogeneous networks.

Findings

CHAT outperforms existing methods on drug-target interaction datasets.

The approach effectively avoids over-smoothing and dependency on meta-paths.

Empirical results demonstrate superior prediction accuracy.

Abstract

Link prediction in heterogeneous networks is crucial for understanding the intricacies of network structures and forecasting their future developments. Traditional methodologies often face significant obstacles, including over-smoothing-wherein the excessive aggregation of node features leads to the loss of critical structural details-and a dependency on human-defined meta-paths, which necessitate extensive domain knowledge and can be inherently restrictive. These limitations hinder the effective prediction and analysis of complex heterogeneous networks. In response to these challenges, we propose the Contrastive Heterogeneous grAph Transformer (CHAT). CHAT introduces a novel sampling-based graph transformer technique that selectively retains nodes of interest, thereby obviating the need for predefined meta-paths. The method employs an innovative connection-aware transformer to encode node sequences and their interconnections with high fidelity, guided by a dual-faceted loss function specifically designed for heterogeneous network link prediction. Additionally, CHAT incorporates an ensemble link predictor that synthesizes multiple samplings to achieve enhanced prediction accuracy. We conducted comprehensive evaluations of CHAT using three distinct drug-target interaction (DTI) datasets. The empirical results underscore CHAT's superior performance, outperforming both general-task approaches and models specialized in DTI prediction. These findings substantiate the efficacy of CHAT in addressing the complex problem of link prediction in heterogeneous networks.