Theory of graph neural networks: representation and learning
DOI10.4171/icm2022/162arXiv2204.07697OpenAlexW4389775256MaRDI QIDQ6200219
Publication date: 22 March 2024
Published in: International Congress of Mathematicians (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2204.07697
Computational learning theory (68Q32) Artificial neural networks and deep learning (68T07) Applications of graph theory (05C90) Learning and adaptive systems in artificial intelligence (68T05) Graph theory (including graph drawing) in computer science (68R10) Graph representations (geometric and intersection representations, etc.) (05C62) Approximations and expansions (41A99) Isomorphism problems in graph theory (reconstruction conjecture, etc.) and homomorphisms (subgraph embedding, etc.) (05C60)
Cites Work
- Unnamed Item
- Unnamed Item
- Polynomial bounds for VC dimension of sigmoidal and general Pfaffian neural networks
- A congruence theorem for trees
- Representations for partially exchangeable arrays of random variables
- An optimal lower bound on the number of variables for graph identification
- On construction and identification of graphs. With contributions by A. Lehman, G. M. Adelson-Velsky, V. Arlazarov, I. Faragev, A. Uskov, I. Zuev, M. Rosenfeld and B. Weisfeiler
- On tables of random numbers
- The Vapnik-Chervonenkis dimension of graph and recursive neural networks
- On the Power of Color Refinement
- On a routing problem
- PEBBLE GAMES AND LINEAR EQUATIONS
- Graph limits and exchangeable random graphs
- Random Graph Isomorphism
- Locality in Distributed Graph Algorithms
- The graph isomorphism disease
- Distributed Computing: A Locality-Sensitive Approach
- 10.1162/153244303321897690
- On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
- Weak models of distributed computing, with connections to modal logic
- Approximation by superpositions of a sigmoidal function
This page was built for publication: Theory of graph neural networks: representation and learning
