Lower and upper bounds for numbers of linear regions of graph convolutional networks-Reference-Cited by-同舟云学术

Lower and upper bounds for numbers of linear regions of graph convolutional networks

Published:2023-11 Issue: Volume:168 Page:394-404
ISSN:0893-6080
Container-title:Neural Networks
language:en
Short-container-title:Neural Networks

Author:

Chen Hao,Wang Yu Guang^ORCID,Xiong Huan

Funder

National Natural Science Foundation of China

Publisher

Elsevier BV

Subject

Artificial Intelligence,Cognitive Neuroscience

Reference51 articles.

1. Random graph isomorphism;Babai;SIAM Journal on Computing,1980

2. The geometry of deep networks: Power diagram subdivision;Balestriero,2019

3. Approximation and estimation bounds for artificial neural networks;Barron;Machine Learning,1994

4. Weisfeiler and Lehman go cellular: CW networks;Bodnar,2021

5. Bodnar, C., Frasca, F., Wang, Y., Otter, N., Montúfar, G. F., Liò, P., et al. (2021). Weisfeiler and Lehman go topological: Message passing simplicial networks. In ICML (pp. 1026–1037).

Cited by 4 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. On the Number of Linear Regions of Convolutional Neural Networks With Piecewise Linear Activations;IEEE Transactions on Pattern Analysis and Machine Intelligence;2024-07

2. Corrigendum to “Lower and upper bounds for numbers of linear regions of graph convolutional networks” [Neural Networks Volume 168, November 2023, Pages 394–404];Neural Networks;2024-03

3. Comparative Analysis of the Linear Regions in ReLU and LeakyReLU Networks;Communications in Computer and Information Science;2023-11-26

4. Empirical Study on the Effect of Residual Networks on the Expressiveness of Linear Regions;Artificial Neural Networks and Machine Learning – ICANN 2023;2023