Exponentially Improving the Complexity of Simulating the Weisfeiler-Lehman Test with Graph Neural Networks.
Anders AamandJustin Y. ChenPiotr IndykShyam NarayananRonitt RubinfeldNicholas SchieferSandeep SilwalTal WagnerPublished in: NeurIPS (2022)
Keyphrases
- neural network
- graph kernels
- random walk
- graph matching
- pattern recognition
- graph construction
- graph representation
- graph theory
- computational complexity
- artificial neural networks
- test cases
- directed graph
- computational cost
- worst case
- graph model
- statistical tests
- directed acyclic graph
- polynomial time complexity
- bounded treewidth
- graph partitioning
- space complexity
- multi layer
- weighted graph
- graph structure
- bipartite graph
- back propagation
- feed forward
- connected components
- decision problems
- fault diagnosis
- software systems