Exploiting Transductive Property of Graph Convolutional Neural Networks with Less Labeling Effort.
Yasir KilicPublished in: CoRR (2021)
Keyphrases
- convolutional neural networks
- labeling effort
- labeled data
- convolutional network
- graph properties
- graph theory
- semi supervised classification
- semi supervised
- transductive learning
- unlabeled data
- graph structure
- bipartite graph
- random walk
- graph model
- graph theoretic
- semi supervised learning
- data sets
- graph representation
- global consistency
- text classification
- weighted graph
- label propagation
- active learning
- learning process
- anti monotonic
- feature space
- neural network