HGMP:Heterogeneous Graph Multi-Task Prompt Learning

TL;DR

This paper introduces HGMP, a multi-task prompt learning framework for heterogeneous graphs that unifies downstream tasks, incorporates contrastive pre-training, and uses feature prompts to improve performance across multiple graph-related tasks.

Contribution

The paper proposes a novel multi-task prompt framework for heterogeneous graphs, including a unified task format, contrastive pre-training strategy, and heterogeneous feature prompts, addressing limitations of existing methods.

Findings

Significantly outperforms baseline methods on public datasets.

Effectively adapts to various heterogeneous graph tasks.

Enhances model performance through feature prompt refinement.

Abstract

The pre-training and fine-tuning methods have gained widespread attention in the field of heterogeneous graph neural networks due to their ability to leverage large amounts of unlabeled data during the pre-training phase, allowing the model to learn rich structural features. However, these methods face the issue of a mismatch between the pre-trained model and downstream tasks, leading to suboptimal performance in certain application scenarios. Prompt learning methods have emerged as a new direction in heterogeneous graph tasks, as they allow flexible adaptation of task representations to address target inconsistency. Building on this idea, this paper proposes a novel multi-task prompt framework for the heterogeneous graph domain, named HGMP. First, to bridge the gap between the pre-trained model and downstream tasks, we reformulate all downstream tasks into a unified graph-level task format. Next, we address the limitations of existing graph prompt learning methods, which struggle to integrate contrastive pre-training strategies in the heterogeneous graph domain. We design a graph-level contrastive pre-training strategy to better leverage heterogeneous information and enhance performance in multi-task scenarios. Finally, we introduce heterogeneous feature prompts, which enhance model performance by refining the representation of input graph features. Experimental results on public datasets show that our proposed method adapts well to various tasks and significantly outperforms baseline methods.