FedTGP: Trainable Global Prototypes with Adaptive-Margin-Enhanced Contrastive Learning for Data and Model Heterogeneity in Federated Learning.
Jianqing ZhangYang LiuYang HuaJian CaoPublished in: CoRR (2024)
Keyphrases
- prior knowledge
- data sets
- learning process
- learning models
- background knowledge
- input data
- probability distribution
- learning problems
- computational model
- experimental data
- unsupervised learning
- data collection
- test data
- human experts
- data structure
- learning mechanism
- database
- learning tasks
- accurate models
- hidden variables
- learning phase
- sensory data
- learning systems
- online learning
- knowledge discovery
- active learning
- training set
- data analysis
- digital libraries
- reinforcement learning
- database systems
- learning algorithm
- databases