HiGNN: Hierarchical Informative Graph Neural Networks for Molecular Property Prediction Equipped with Feature-Wise Attention.
Weimin ZhuYi ZhangDuancheng ZhaoJianrong XuLing WangPublished in: CoRR (2022)
Keyphrases
- neural network
- protein function prediction
- prediction accuracy
- prediction model
- fuzzy logic
- artificial neural networks
- artificial neural networks to predict
- multi layer
- graph structure
- multi layer perceptron
- prediction error
- random walk
- pattern recognition
- neural network ensemble
- multilayer perceptron
- neural networks and support vector machines
- global consistency
- graph theoretic
- graph representation
- feature vectors
- graph model
- hierarchical structure
- genetic algorithm
- prediction algorithm
- structured data
- preprocessing stage
- feature extraction
- graph properties
- self organizing maps