Generalized Graph Prompt: Toward a Unification of Pre-Training and Downstream Tasks on Graphs

TL;DR

This paper introduces GraphPrompt, a unified framework for pre-training and prompting on graphs that employs learnable prompts and hierarchical prompt design to improve performance across various downstream tasks.

Contribution

It proposes a universal task template for graphs, a learnable prompt mechanism, and extends to GraphPrompt+ with generalized pre-training tasks and multi-layer prompts.

Findings

Effective across five public datasets

Unifies pre-training and downstream tasks

Enhances performance with hierarchical prompts

Abstract

Graph neural networks have emerged as a powerful tool for graph representation learning, but their performance heavily relies on abundant task-specific supervision. To reduce labeling requirement, the "pre-train, prompt" paradigms have become increasingly common. However, existing study of prompting on graphs is limited, lacking a universal treatment to appeal to different downstream tasks. In this paper, we propose GraphPrompt, a novel pre-training and prompting framework on graphs. GraphPrompt not only unifies pre-training and downstream tasks into a common task template but also employs a learnable prompt to assist a downstream task in locating the most relevant knowledge from the pre-trained model in a task-specific manner. To further enhance GraphPrompt in these two stages, we extend it into GraphPrompt+ with two major enhancements. First, we generalize several popular graph pre-training tasks beyond simple link prediction to broaden the compatibility with our task template. Second, we propose a more generalized prompt design that incorporates a series of prompt vectors within every layer of the pre-trained graph encoder, in order to capitalize on the hierarchical information across different layers beyond just the readout layer. Finally, we conduct extensive experiments on five public datasets to evaluate and analyze GraphPrompt and GraphPrompt+.