CurvDrop: A Ricci Curvature Based Approach to Prevent Graph Neural Networks from Over-Smoothing and Over-Squashing.

Yang Liu|Chuan Zhou|Shirui Pan|Jia Wu|Zhao Li|Hongyang Chen|Peng Zhang


Anthology ID:DBLP:conf/www/Liu0P00C023
Volume:Proceedings of the ACM Web Conference 2023, WWW 2023, Austin, TX, USA, 30 April 2023 - 4 May 2023
Year:2023
Venue:The Web Conference (WWW)
Publisher:ACM
Pages:221-230
URL:https://doi.org/10.1145/3543507.3583269
DOI:https://doi.org/10.1145/3543507.3583269
DBLP:conf/www/Liu0P00C023
BibTeX:
@inproceedings{liu-2023-curvdrop, author = {Yang Liu and Chuan Zhou and Shirui Pan and Jia Wu and Zhao Li and Hongyang Chen and Peng Zhang}, editor = {Ying Ding and Jie Tang and Juan F. Sequeda and Lora Aroyo and Carlos Castillo and Geert-Jan Houben}, title = {{CurvDrop: A Ricci Curvature Based Approach to Prevent Graph Neural Networks from Over-Smoothing and Over-Squashing}}, booktitle = {{Proceedings of the ACM Web Conference 2023, WWW 2023, Austin, TX, USA, 30 April 2023 - 4 May 2023}}, pages = {221--230}, publisher = {ACM}, year = {2023}, url = {https://doi.org/10.1145/3543507.3583269}, doi = {https://doi.org/10.1145/3543507.3583269} }