Unified Graph Prompt Learning via Low-Rank Graph Message Prompting

TL;DR

This paper introduces LR-GMP, a unified low-rank graph prompt learning method that prompts all graph components simultaneously, improving generalization and robustness across various graph tasks.

Contribution

It proposes a novel Low-Rank GMP approach that unifies prompting for all graph components, addressing limitations of existing GDPs.

Findings

LR-GMP outperforms existing GDPs on multiple benchmarks.

Unified prompting improves robustness and generalization.

Extensive experiments validate the effectiveness of LR-GMP.

Abstract

Graph Data Prompt (GDP), which introduces specific prompts in graph data for efficiently adapting pre-trained GNNs, has become a mainstream approach to graph fine-tuning learning problem. However, existing GDPs have been respectively designed for distinct graph component (e.g., node features, edge features, edge weights) and thus operate within limited prompt spaces for graph data. To the best of our knowledge, it still lacks a unified prompter suitable for targeting all graph components simultaneously. To address this challenge, in this paper, we first propose to reinterpret a wide range of existing GDPs from an aspect of Graph Message Prompt (GMP) paradigm. Based on GMP, we then introduce a novel graph prompt learning approach, termed Low-Rank GMP (LR-GMP), which leverages low-rank prompt representation to achieve an effective and compact graph prompt learning. Unlike traditional GDPs that target distinct graph components separately, LR-GMP concurrently performs prompting on all graph components in a unified manner, thereby achieving significantly superior generalization and robustness on diverse downstream tasks. Extensive experiments on several graph benchmark datasets demonstrate the effectiveness and advantages of our proposed LR-GMP.