Path Integral Based Convolution and Pooling for Graph Neural Networks.
Zheng MaJunyu XuanYu Guang WangMing LiPietro LióPublished in: CoRR (2020)
Keyphrases
- neural network
- graph representation
- graph based algorithm
- solution path
- shortest path problem
- artificial neural networks
- multi layer
- neural nets
- genetic algorithm
- graph model
- graph structure
- graph theory
- random walk
- recurrent neural networks
- integral equation
- pattern recognition
- neural network model
- path length
- weighted graph
- structured data
- directed acyclic graph
- shortest path
- activation function
- hamiltonian path
- edge weights
- fuzzy systems
- directed graph
- bipartite graph
- spanning tree
- back propagation
- endpoints
- graph construction
- fuzzy logic
- feed forward
- graph matching