The Snowflake Hypothesis: Training and Powering GNN with One Node One Receptive Field-Reference-Cited by-同舟云学术

The Snowflake Hypothesis: Training and Powering GNN with One Node One Receptive Field

Published:2024-08-24 Issue: Volume:2 Page:3152-3163
ISSN:
Container-title:Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
language:
Short-container-title:

Author:

Wang Kun¹^ORCID,Li Guohao²^ORCID,Wang Shilong³^ORCID,Zhang Guibin⁴^ORCID,Wang Kai⁵^ORCID,You Yang⁵^ORCID,Fang Junfeng¹^ORCID,Peng Xiaojiang⁶^ORCID,Liang Yuxuan⁷^ORCID,Wang Yang¹^ORCID

Affiliation:

1. University of Science and Technology of China (USTC), Hefei, China

2. Oxford University, London, United Kingdom

3. University of Science and Technology of China, Hefei, China

4. International Digital Economy Academy, Shanghai, China

5. National University of Singapore, Singapore, Singapore

6. Shenzhen Technology University, shenzhen, China

7. The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China

Funder

National Natural Science Foundation of China

Publisher

ACM

Link

https://dl.acm.org/doi/pdf/10.1145/3637528.3671766

Reference72 articles.

1. Sami Abu-El-Haija, Amol Kapoor, Bryan Perozzi, and Joonseok Lee. 2020. N-gcn: Multi-scale graph convolution for semi-supervised node classification. In uncertainty in artificial intelligence. PMLR, 841--851.

2. Anonymous. 2023. Graph Lottery Ticket Automated. In Submitted to The Twelfth International Conference on Learning Representations. https://openreview.net/forum?id=nmBjBZoySX under review.

3. What is the state of neural network pruning;Blalock Davis;Proceedings of machine learning and systems,2020

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. arXiv preprint arXiv:1801.10247 (2018).