A Prototype-Based Knowledge Distillation Framework for Heterogeneous Federated Learning.
Feng LyuCheng TangYongheng DengTong LiuYongmin ZhangYaoxue ZhangPublished in: ICDCS (2023)
Keyphrases
- knowledge acquisition
- prior knowledge
- learning scheme
- learning systems
- main contribution
- learning algorithm
- learning process
- learned knowledge
- learning mechanism
- effective learning
- knowledge transfer
- distributed data sources
- neural network
- design principles
- learning problems
- learning tasks
- supervised learning
- knowledge representation
- domain knowledge
- active learning
- reinforcement learning
- background knowledge
- domain experts
- concept maps
- multi task
- knowledge level
- probabilistic model
- distributed learning