Contrastive pre-training of GNNs on heterogeneous graphs
While graph neural networks (GNNs) emerge as the state-of-the-art representation learning methods on graphs, they often require a large amount of labeled data to achieve satisfactory performance, which is often expensive or unavailable. To relieve the label scarcity issue, some pre-training strategi...
Saved in:
Main Authors: | JIANG, Xunqiang, LU, Yuanfu, FANG, Yuan, SHI, Chuan |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2021
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/6889 https://ink.library.smu.edu.sg/context/sis_research/article/7892/viewcontent/124.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Pre-training on large-scale heterogeneous graph
by: JIANG, Xunqiang, et al.
Published: (2021) -
Learning to pre-train graph neural networks
by: LU, Yuanfu, et al.
Published: (2021) -
Graphprompt: Unifying pre-training and downstream tasks for graph neural networks
by: LIU, Zemin, et al.
Published: (2023) -
Masked autoencoders for contrastive learning of heterogenous graphs
by: Srinthi Nachiyar D/O Thangamuthu
Published: (2024) -
Dynamic heterogeneous graph embedding via heterogeneous Hawkes process
by: JI, Yugang, et al.
Published: (2021)