Federated Learning on Heterogeneous and Long-Tailed Data via Classifier Re-Training with Federated Features.
Xinyi ShangYang LuGang HuangHanzi WangPublished in: IJCAI (2022)
Keyphrases
- training examples
- learning algorithm
- training data
- data sets
- prior knowledge
- training samples
- learning models
- data analysis
- feature set
- supervised learning
- data sources
- labeled data
- learned models
- distributed data
- learning process
- input data
- labeled training data
- digital libraries
- extracted features
- feature values
- supervised training
- training process
- positive and negative samples
- labeled instances
- classification method
- reinforcement learning
- machine learning
- data points
- classification process
- heterogeneous data
- classification accuracy
- feature vectors
- feature space
- feature selection