The game theoretic p-Laplacian and semi-supervised learning with few labels.
Jeff CalderPublished in: CoRR (2017)
Keyphrases
- game theoretic
- semi supervised learning
- label propagation
- multi label classification
- multi instance learning
- labeled examples
- game theory
- semi supervised
- training data
- unlabeled data
- partially labeled
- unlabeled samples
- decision problems
- graph laplacian
- labeled data
- machine learning
- supervised learning
- unsupervised learning
- nash equilibrium
- active learning
- manifold regularization
- co training
- trust model
- semi supervised classification
- class labels
- graph based semi supervised learning
- unlabeled instances
- pairwise
- graph construction
- labeled instances
- pairwise constraints
- label information
- data sets
- multi label
- state space
- labeled and unlabeled data
- upper bound
- combinatorial auctions
- object recognition
- computational complexity
- multi agent
- worst case
- conditional random fields