Deep Heterogeneous Graph Neural Networks via Similarity Regularization Loss and Hierarchical Fusion.
Zhilong XiongJia CaiPublished in: ICDM (Workshops) (2022)
Keyphrases
- neural network
- similarity measure
- multi layer
- pattern recognition
- graph laplacian
- artificial neural networks
- solution path
- back propagation
- similarity graph
- graph structure
- distance measure
- inexact graph matching
- weighted graph
- match scores
- graph representation
- directed graph
- neural network model
- multiple layers
- graph model
- genetic algorithm
- graph theory
- multi sensor
- neural nets
- similarity function
- hierarchical structure
- euclidean distance
- structured data
- random walk
- fuzzy logic
- multilayer perceptron
- similarity metric
- information fusion
- data fusion
- spanning tree
- regularization parameter
- edit distance
- semantic similarity
- energy function
- similarity search
- unsupervised learning
- maximum common subgraph