Two-Stage Clustering for Federated Learning with Pseudo Mini-batch SGD Training on Non-IID Data.
Jianqing WengSongzhi SuXiaoliang FanPublished in: ChineseCSCW (1) (2021)
Keyphrases
- data sets
- data analysis
- training data
- data sources
- online learning
- data points
- original data
- supervised learning
- database
- prior knowledge
- xml documents
- data objects
- clustering algorithm
- distributed data
- high dimensional data
- knowledge discovery
- spectral clustering
- categorical data
- clustering method
- data collection
- data structure
- machine learning
- training examples
- learning tasks
- k means
- learning process
- training process
- feature selection
- clustering analysis