Graphprompt: Unifying pre-training and downstream tasks for graph neural networks

• Main Authors: LIU, Zemin, YU, Xingtong, FANG, Yuan, ZHANG, Xinming
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Graph neural networks; pre-training; prompt; few-shot learning; Information Security
• Online Access: https://ink.library.smu.edu.sg/sis_research/8191; https://ink.library.smu.edu.sg/context/sis_research/article/9194/viewcontent/TheWebConf23_GraphPrompt.pdf
• Institution: Singapore Management University

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks (GNNs) have emerged as a powerful tool for graph representation learning, in an end-to-end supervised setting, their performance heavily relies on a large amount of task-specific supervision. To reduce labeling requirement, the "pre-train, fine-tune"and "pre-train, prompt"paradigms have become increasingly common. In particular, prompting is a popular alternative to fine-tuning in natural language processing, which is designed to narrow the gap between pre-training and downstream objectives in a task-specific manner. However, existing study of prompting on graphs is still 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. Finally, we conduct extensive experiments on five public datasets to evaluate and analyze GraphPrompt.