CurvDrop: A Ricci Curvature Based Approach to Prevent Graph Neural Networks from Over-Smoothing and Over-Squashing-Reference-Cited by-同舟云学术

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

Published:2023-04-30 Issue: Volume: Page:
ISSN:
Container-title:Proceedings of the ACM Web Conference 2023
language:
Short-container-title:

Author:

Liu Yang¹^ORCID,Zhou Chuan²^ORCID,Pan Shirui³^ORCID,Wu Jia⁴^ORCID,Li Zhao⁵^ORCID,Chen Hongyang⁶^ORCID,Zhang Peng⁷^ORCID

Affiliation:

1. Academy of Mathematics and Systems Science, Chinese Academy of Sciences, China

2. AMSS, Chinese Academy of Science, China and School of Cyber Security, University of Chinese Academy of Science, China

3. School of Information and Communication Technology, Griffith University, Australia

4. School of Computing, Macquarie University, Australia

5. Hangzhou link2do Technology, China

6. Research Center for Graph Computing, Zhejiang Lab, China

7. Cyberspace Institute of Advanced Technology, Guangzhou University, China

Funder

Australian Research Council (ARC) Projects

Key Research Project of Zhejiang Lab

National Key Research and Development Program of China

Joint Research Fund of Guangzhou University

CAS Project for Young Scientists in Basic Research

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3543507.3583269

Reference41 articles.

1. Uri Alon and Eran Yahav . 2020 . On the Bottleneck of Graph Neural Networks and its Practical Implications . In International Conference on Learning Representations. Uri Alon and Eran Yahav. 2020. On the Bottleneck of Graph Neural Networks and its Practical Implications. In International Conference on Learning Representations.

2. Shuliang Bai , An Huang , Linyuan Lu , and Shing-Tung Yau . 2020. On the sum of Ricci-curvatures for weighted graphs. arXiv preprint arXiv:2001.01776 ( 2020 ). Shuliang Bai, An Huang, Linyuan Lu, and Shing-Tung Yau. 2020. On the sum of Ricci-curvatures for weighted graphs. arXiv preprint arXiv:2001.01776 (2020).

3. Aleksandar Bojchevski , Oleksandr Shchur , Daniel Zügner , and Stephan Günnemann . 2018 . Netgan: Generating graphs via random walks . In International conference on machine learning. PMLR, 610–619 . Aleksandar Bojchevski, Oleksandr Shchur, Daniel Zügner, and Stephan Günnemann. 2018. Netgan: Generating graphs via random walks. In International conference on machine learning. PMLR, 610–619.

4. Measuring and Relieving the Over-Smoothing Problem for Graph Neural Networks from the Topological View

5. Jie Chen , Tengfei Ma , and Cao Xiao . 2018 . FastGCN: Fast learning with graph convolutional networks via importance sampling . In International Conference on Learning Representations. International Conference on Learning Representations, ICLR. Jie Chen, Tengfei Ma, and Cao Xiao. 2018. FastGCN: Fast learning with graph convolutional networks via importance sampling. In International Conference on Learning Representations. International Conference on Learning Representations, ICLR.

Cited by 8 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Efficient and Provable Effective Resistance Computation on Large Graphs: An Index-based Approach;Proceedings of the ACM on Management of Data;2024-05-29

2. RicciNet: Deep Clustering via A Riemannian Generative Model;Proceedings of the ACM Web Conference 2024;2024-05-13

3. Meta Structure Search for Link Weight Prediction in Heterogeneous Graphs;ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP);2024-04-14

4. Conditional Shift-Robust Conformal Prediction for Graph Neural Network;2024

5. DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing;2023 IEEE International Conference on Data Mining (ICDM);2023-12-01