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 rely 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-train model in a task-specific manner. Finally, we conduct extensive experiments on five public datasets to evaluate and analyze GraphPrompt.
Generalized Graph Prompt: Toward a Unification of Pre-Training and Downstream Tasks on Graphs
University of Science and Technology of China(中国科学技术大学);Singapore Management University(新加坡管理大学);National University of Singapore(新加坡国立大学);Tecent AI(腾讯人工智能)
Università della Svizzera italiana(瑞士意大利语大学);UiT the Arctic University of Norway(挪威北极大学);NORCE, The Norwegian Research Centre(挪威NORCE研究中心);Politecnico di Milano(米兰理工大学)
Unifying Detection and Adaptation in Task-Free Continual Learning
School of Control Science and Engineering, Shandong University(山东大学控制科学与工程学院);The Hong Kong University of Science and Technology(香港科技大学);Shandong University(山东大学);Qilu Hospital of Shandong University(山东大学齐鲁医院)
Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization
Helmholtz Munich(海德堡大学慕尼黑分校);Max Planck Institute for Biological Cybernetics(生物 cybernetics 最大计划研究所);Princeton University(普林斯顿大学);University of Tübingen(图宾根大学)
UniRTL: Unifying Code and Graph for Robust RTL Representation Learning
Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR(计算机科学与工程系,香港中文大学,香港特别行政区);Noah's Ark Lab, Huawei, Hong Kong SAR(华为诺亚实验室,香港特别行政区)
Trinity: Unifying Class-Agnostic Terrain and Semantic Segmentation for Unstructured Outdoor Environments by Leveraging Synthetic Data
Institute of Robotics and Mechatronics, German Aerospace Center (DLR)(机器人与机电系统研究所,德国航空航天中心(DLR));Federal Institute of Technology Zurich (ETH Zurich)(苏黎世联邦理工学院(ETH Zurich));Robotics and AI Institute (RAI)(机器人与人工智能研究所(RAI))