CLEAR: Cluster-based Prompt Learning on Heterogeneous Graphs

TL;DR

CLEAR introduces a cluster-based prompt learning approach that leverages meta-paths in heterogeneous graphs, improving task performance by aligning pretext and downstream objectives and capturing high-order semantics.

Contribution

The paper proposes a novel cluster prompt method that incorporates meta-paths for enhanced heterogeneous graph learning, addressing limitations of feature prompts.

Findings

Achieves up to 5% improvement in F1 score for node classification.

Outperforms state-of-the-art models on multiple downstream tasks.

Effectively captures high-order semantic information through meta-paths.

Abstract

Prompt learning has attracted increasing attention in the graph domain as a means to bridge the gap between pretext and downstream tasks. Existing studies on heterogeneous graph prompting typically use feature prompts to modify node features for specific downstream tasks, which do not concern the structure of heterogeneous graphs. Such a design also overlooks information from the meta-paths, which are core to learning the high-order semantics of the heterogeneous graphs. To address these issues, we propose CLEAR, a Cluster-based prompt LEARNING model on heterogeneous graphs. We present cluster prompts that reformulate downstream tasks as heterogeneous graph reconstruction. In this way, we align the pretext and downstream tasks to share the same training objective. Additionally, our cluster prompts are also injected into the meta-paths such that the prompt learning process incorporates high-order semantic information entailed by the meta-paths. Extensive experiments on downstream tasks confirm the superiority of CLEAR. It consistently outperforms state-of-the-art models, achieving up to 5% improvement on the F1 metric for node classification.