HGPROMPT: Bridging Homogeneous and Heterogeneous Graphs for Few-shot Prompt Learning

TL;DR

HGPROMPT introduces a unified prompt learning framework that effectively bridges the gap between pre-training and downstream tasks for both homogeneous and heterogeneous graphs, enhancing few-shot learning performance.

Contribution

The paper presents a novel dual-template and dual-prompt design to unify pre-training and downstream tasks across homogeneous and heterogeneous graphs, addressing divergence issues.

Findings

Effective in few-shot learning scenarios

Outperforms existing methods on multiple datasets

Bridges gap between pre-training and downstream tasks

Abstract

Graph neural networks (GNNs) and heterogeneous graph neural networks (HGNNs) are prominent techniques for homogeneous and heterogeneous graph representation learning, yet their performance in an end-to-end supervised framework greatly depends on the availability of task-specific supervision. To reduce the labeling cost, pre-training on self-supervised pretext tasks has become a popular paradigm,but there is often a gap between the pre-trained model and downstream tasks, stemming from the divergence in their objectives. To bridge the gap, prompt learning has risen as a promising direction especially in few-shot settings, without the need to fully fine-tune the pre-trained model. While there has been some early exploration of prompt-based learning on graphs, they primarily deal with homogeneous graphs, ignoring the heterogeneous graphs that are prevalent in downstream applications. In this paper, we propose HGPROMPT, a novel pre-training and prompting framework to unify not only pre-training and downstream tasks but also homogeneous and heterogeneous graphs via a dual-template design. Moreover, we propose dual-prompt in HGPROMPT to assist a downstream task in locating the most relevant prior to bridge the gaps caused by not only feature variations but also heterogeneity differences across tasks. Finally, we thoroughly evaluate and analyze HGPROMPT through extensive experiments on three public datasets.