Oversquashing in GNNs through the lens of information contraction and graph expansion-Reference-Cited by-同舟云学术

Oversquashing in GNNs through the lens of information contraction and graph expansion

Published:2022-09-27 Issue: Volume: Page:
ISSN:
Container-title:2022 58th Annual Allerton Conference on Communication, Control, and Computing (Allerton)
language:
Short-container-title:

Author:

Banerjee Pradeep Kr.¹,Karhadkar Kedar²,Wang Yu Guang³,Alon Uri⁴,Montufar Guido²

Affiliation:

1. MPI MiS

2. UCLA

3. SJTU

4. CMU

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/9929313/9929314/09929363.pdf?arnumber=9929363

Reference60 articles.

1. On the maximum tolerable noise of k-input gates for reliable computation by formulas

2. Expander graphs - applications and combinatorial constructions;wigderson;A 3-hour tutorial Pseudorandomness in Mathematical Structures Workshop,2010

3. Ricci curvature of Markov chains on metric spaces

4. On contraction properties of Markov kernels

5. Perturbation methods of the theory of Gibbsian fields

Cited by 6 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. Molecular representation contrastive learning via transformer embedding to graph neural networks;Applied Soft Computing;2024-10

2. Design your own universe: a physics-informed agnostic method for enhancing graph neural networks;International Journal of Machine Learning and Cybernetics;2024-09-02

3. Addressing Over-Squashing in GNNs with Graph Rewiring and Ordered Neurons;2024 International Joint Conference on Neural Networks (IJCNN);2024-06-30

4. CINA: Curvature-Based Integrated Network Alignment with Hypergraph;2024 IEEE 40th International Conference on Data Engineering (ICDE);2024-05-13

5. Boundary representation compatible feature recognition for manufacturing CAD models;Manufacturing Letters;2023-08