Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting-Reference-Cited by-同舟云学术

Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting

Author:

Bouritsas Giorgos¹^ORCID,Frasca Fabrizio²,Zafeiriou Stefanos¹^ORCID,Bronstein Michael M.³

Affiliation:

1. Department of Computing, Imperial College London, London, U.K.

2. Department of Computing, Imperial College London, U.K.

3. Department of Computer Science, University of Oxford, U.K.

Funder

ERC Consolidator

Department of Computing, Imperial College London

EPSRC Fellowship DEFORM: Large Scale Shape Analysis of Deformable Models of Humans

Google Faculty Award

Google Faculty Award and the Royal Society Wolfson Research Merit Award

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Applied Mathematics,Artificial Intelligence,Computational Theory and Mathematics,Computer Vision and Pattern Recognition,Software

Link

Reference115 articles.

1. On the equivalence between graph isomorphism testing and function approximation with GNNs;chen;Proc Adv Neural Inf Process Syst,0

3. What graph neural networks cannot learn: Depth vs width;loukas;Proc Int Conf Learn Representations,0

4. Attention is all you need;vaswani;Proc Adv Neural Inf Process Syst,0

5. Convolutional sequence to sequence learning;gehring;Proc Int Conf Mach Learn,0

Cited by 91 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