Noisy Positive-Unlabeled Learning with Self-Training for Speculative Knowledge Graph Reasoning.
Ruijie WangBaoyu LiYichen LuDachun SunJinning LiYuchen YanShengzhong LiuHanghang TongTarek F. AbdelzaherPublished in: CoRR (2023)
Keyphrases
- learning systems
- knowledge acquisition
- learning algorithm
- training set
- prior knowledge
- unsupervised learning
- supervised learning
- procedural knowledge
- semi supervised learning
- learning process
- reinforcement learning
- knowledge base
- positive and unlabeled examples
- reasoning processes
- intelligent behavior
- solving problems
- active learning
- domain experts
- background knowledge
- graph structure
- positive examples
- knowledge management
- learned knowledge
- knowledge representation
- domain knowledge
- machine learning
- learning tasks
- graph theory
- directed acyclic graph
- online learning
- reasoning process
- declarative knowledge