/FedFA

The open-souce code of FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data, accepted by IEEE TMC.

Primary LanguageJupyter Notebook

FedFA

The open-source code of FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data, accepted by IEEE TMC: https://ieeexplore.ieee.org/document/10286887. Arxiv: https://arxiv.org/abs/2211.09299.

Please directly run our example Jupiter files for your codes.

Citation

If our code has been helpful to you, we would appreciate a citation as follows:

@ARTICLE {FedFA_Tailin2022, author = {T. Zhou and J. Zhang and D. K. Tsang}, journal = {IEEE Transactions on Mobile Computing}, title = {FedFA: Federated Learning with Feature Anchors to Align Features and Classifiers for Heterogeneous Data}, year = {2023}, number = {01}, issn = {1558-0660}, pages = {1-12}, doi = {10.1109/TMC.2023.3325366}, month = {oct} }