Heterogeneous graph transformer with poly-tokenization
Graph neural networks have shown widespread success for learning on graphs, but they still face fundamental drawbacks, such as limited expressive power, over-smoothing, and over-squashing. Meanwhile, the transformer architecture offers a potential solution to these issues. However, existing graph tr...
Saved in:
Main Authors: | LU, Zhiyuan, FANG, Yuan, YANG, Cheng, SHI, Chuan |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2024
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/9678 https://ink.library.smu.edu.sg/context/sis_research/article/10678/viewcontent/IJCAI24_PHGT.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Dense graph pattern mining and visualization
by: WANG NAN
Published: (2011) -
CSV: Visualizing and mining cohesive subgraphs
by: Wangt, N., et al.
Published: (2013) -
End-to-end open-set semi-supervised node classification with out-of-distribution detection
by: HUANG, Tiancheng, et al.
Published: (2022) -
RELATIONSHIP DISCOVERY FROM OPEN KNOWLEDGE GRAPHS AND ITS APPLICATIONS
by: YANG YUEJI
Published: (2021) -
Systematic assessment of protein interaction data using graph topology approaches
by: CHEN JIN
Published: (2010)