MHAT: An efficient model-heterogenous aggregation training scheme for federated learning.
Li HuHongyang YanLang LiZijie PanXiaozhang LiuZulong ZhangPublished in: Inf. Sci. (2021)
Keyphrases
- learning scheme
- prior knowledge
- learning process
- computational model
- online learning
- learning models
- objective function
- learning systems
- probabilistic model
- structured prediction
- neural nets
- supervised learning
- management system
- active learning
- data model
- high level
- learning algorithm
- learning speed
- radial basis function network
- neural network
- data sources
- machine learning