ASIAM-HGNN: Automatic Selection and Interpretable Aggregation of Meta-Path Instances for Heterogeneous Graph Neural Network.
Xiaojun LouGuanjun LiuJian LiPublished in: Comput. Informatics (2023)
Keyphrases
- automatic selection
- neural network
- strongly connected
- graph transformation
- directed graph
- graph structure
- structured data
- random walk
- genetic algorithm
- solution path
- meta level
- back propagation
- root node
- pattern recognition
- artificial neural networks
- shortest path problem
- shortest path
- classification rules
- graph representation
- weighted graph
- graph theory
- directed acyclic graph
- data aggregation
- connected components
- graph theoretic
- heterogeneous networks
- bp neural network
- path length
- image segmentation
- subgraph isomorphism
- learning algorithm
- radial basis function