FedAG:A Federated Learning Method Based on Data Importance Weighted Aggregation.
Mengchu XuYan ZengMeiting XueJilin ZhangJian WanMingyao ZhouYilin WenYukun ShiPublished in: ICCC (2023)
Keyphrases
- synthetic data
- prior knowledge
- training data
- input data
- correlation analysis
- bayesian methods
- noisy data
- high accuracy
- learned models
- database
- data sources
- cost function
- learning process
- data structure
- high quality
- data sets
- learning scheme
- similarity measure
- prior information
- statistical methods
- test data
- objective function
- support vector machine
- image data
- detection method
- data collection
- background knowledge
- classification accuracy
- learning models
- pairwise
- distributed data
- missing data
- segmentation method
- learning algorithm
- machine learning
- significant improvement