HGPrompt: Bridging homogeneous and heterogeneous graphs for few-shot prompt learning
Graph neural networks (GNNs) and heterogeneous graph neural networks (HGNNs) are prominent techniques for homogeneous and heterogeneous graph representation learning, yet their performance in an end-to-end supervised framework greatly depends on the availability of task-specific supervision. To redu...
Saved in:
Main Authors: | , , , |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2024
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/8712 https://ink.library.smu.edu.sg/context/sis_research/article/9715/viewcontent/29596_Article_Text_33650_1_2_20240324.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
id |
sg-smu-ink.sis_research-9715 |
---|---|
record_format |
dspace |
spelling |
sg-smu-ink.sis_research-97152024-04-04T08:53:07Z HGPrompt: Bridging homogeneous and heterogeneous graphs for few-shot prompt learning YU, Xingtong FANG, Yuan LIU, Zemin ZHANG, Xinming Graph neural networks (GNNs) and heterogeneous graph neural networks (HGNNs) are prominent techniques for homogeneous and heterogeneous graph representation learning, yet their performance in an end-to-end supervised framework greatly depends on the availability of task-specific supervision. To reduce the labeling cost, pre-training on selfsupervised pretext tasks has become a popular paradigm, but there is often a gap between the pre-trained model and downstream tasks, stemming from the divergence in their objectives. To bridge the gap, prompt learning has risen as a promising direction especially in few-shot settings, without the need to fully fine-tune the pre-trained model. While there has been some early exploration of prompt-based learning on graphs, they primarily deal with homogeneous graphs, ignoring the heterogeneous graphs that are prevalent in downstream applications. In this paper, we propose HGPROMPT, a novel pre-training and prompting framework to unify not only pre-training and downstream tasks but also homogeneous and heterogeneous graphs via a dual-template design. Moreover, we propose dual-prompt in HGPROMPT to assist a downstream task in locating the most relevant prior to bridge the gaps caused by not only feature variations but also heterogeneity differences across tasks. Finally, we thoroughly evaluate and analyze HGPROMPT through extensive experiments on three public datasets. 2024-02-01T08:00:00Z text application/pdf https://ink.library.smu.edu.sg/sis_research/8712 https://ink.library.smu.edu.sg/context/sis_research/article/9715/viewcontent/29596_Article_Text_33650_1_2_20240324.pdf http://creativecommons.org/licenses/by-nc-nd/4.0/ Research Collection School Of Computing and Information Systems eng Institutional Knowledge at Singapore Management University Databases and Information Systems Graphics and Human Computer Interfaces |
institution |
Singapore Management University |
building |
SMU Libraries |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
SMU Libraries |
collection |
InK@SMU |
language |
English |
topic |
Databases and Information Systems Graphics and Human Computer Interfaces |
spellingShingle |
Databases and Information Systems Graphics and Human Computer Interfaces YU, Xingtong FANG, Yuan LIU, Zemin ZHANG, Xinming HGPrompt: Bridging homogeneous and heterogeneous graphs for few-shot prompt learning |
description |
Graph neural networks (GNNs) and heterogeneous graph neural networks (HGNNs) are prominent techniques for homogeneous and heterogeneous graph representation learning, yet their performance in an end-to-end supervised framework greatly depends on the availability of task-specific supervision. To reduce the labeling cost, pre-training on selfsupervised pretext tasks has become a popular paradigm, but there is often a gap between the pre-trained model and downstream tasks, stemming from the divergence in their objectives. To bridge the gap, prompt learning has risen as a promising direction especially in few-shot settings, without the need to fully fine-tune the pre-trained model. While there has been some early exploration of prompt-based learning on graphs, they primarily deal with homogeneous graphs, ignoring the heterogeneous graphs that are prevalent in downstream applications. In this paper, we propose HGPROMPT, a novel pre-training and prompting framework to unify not only pre-training and downstream tasks but also homogeneous and heterogeneous graphs via a dual-template design. Moreover, we propose dual-prompt in HGPROMPT to assist a downstream task in locating the most relevant prior to bridge the gaps caused by not only feature variations but also heterogeneity differences across tasks. Finally, we thoroughly evaluate and analyze HGPROMPT through extensive experiments on three public datasets. |
format |
text |
author |
YU, Xingtong FANG, Yuan LIU, Zemin ZHANG, Xinming |
author_facet |
YU, Xingtong FANG, Yuan LIU, Zemin ZHANG, Xinming |
author_sort |
YU, Xingtong |
title |
HGPrompt: Bridging homogeneous and heterogeneous graphs for few-shot prompt learning |
title_short |
HGPrompt: Bridging homogeneous and heterogeneous graphs for few-shot prompt learning |
title_full |
HGPrompt: Bridging homogeneous and heterogeneous graphs for few-shot prompt learning |
title_fullStr |
HGPrompt: Bridging homogeneous and heterogeneous graphs for few-shot prompt learning |
title_full_unstemmed |
HGPrompt: Bridging homogeneous and heterogeneous graphs for few-shot prompt learning |
title_sort |
hgprompt: bridging homogeneous and heterogeneous graphs for few-shot prompt learning |
publisher |
Institutional Knowledge at Singapore Management University |
publishDate |
2024 |
url |
https://ink.library.smu.edu.sg/sis_research/8712 https://ink.library.smu.edu.sg/context/sis_research/article/9715/viewcontent/29596_Article_Text_33650_1_2_20240324.pdf |
_version_ |
1814047473513005056 |