Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspaces.
Saeed VahidianMahdi MorafahWeijia WangVyacheslav KungurtsevChen ChenMubarak ShahBill LinPublished in: CoRR (2022)
Keyphrases
- data sets
- data distribution
- prior knowledge
- synthetic data
- background knowledge
- learning process
- data points
- original data
- raw data
- user defined
- data processing
- knowledge discovery
- data sources
- learning algorithm
- image data
- probability distribution
- data collection
- data analysis
- high quality
- database
- uniformly distributed
- distributed data
- central server
- data quality
- high dimensional data
- online learning
- data mining