Publication Type

Journal Article

Version

publishedVersion

Publication Date

6-2024

Abstract

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. In particular, GraphPrompt adopts simple yet effective designs in both pre-training and prompt tuning: During pre-training, a link prediction-based task is used to materialize the task template; during prompt tuning, a learnable prompt vector is applied to the ReadOut layer of the graph encoder. To further enhance GraphPrompt in these two stages, we extend it into GraphPrompt+ with two major enhancements. First, we generalize a few 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+.

Keywords

Few-shot learning, Fine tuning, Graph mining, Graph neural networks, Metalearning, Pre-training, Prompting, Representation learning, Task analysis, Tuning

Discipline

Databases and Information Systems | Graphics and Human Computer Interfaces

Publication

IEEE Transactions on Knowledge and Data Engineering

Volume

36

Issue

11

First Page

6237

Last Page

6250

ISSN

1041-4347

Identifier

10.1109/TKDE.2024.3419109

Publisher

Institute of Electrical and Electronics Engineers

Additional URL

https://doi.org/10.1109/TKDE.2024.3419109

Download

Share

COinS