Multi-Task Learning for Federated Classification and Regression

doi:doi:10.57702/ye0h42cx

Multi-Task Learning for Federated Classification and Regression

The proposed algorithm allows personalizing the learning model for each participant without sharing the training data and improves the performance, compared to that of the locally trained models provide. The method is especially beneﬁcial in the case of the low volumes of data available to individual participants.

BibTex:

@dataset{Aleksei_Ponomarenko-Timofeev_and_Olga_Galinina_and_Ravikumar_Balakrishnan_and_Nageen_Himayat_and_Sergey_Andreev_and_Yevgeni_Koucheryavy_2024,
    abstract = {The proposed algorithm allows personalizing the learning model for each participant without sharing the training data and improves the performance, compared to that of the locally trained models provide. The method is especially beneﬁcial in the case of the low volumes of data available to individual participants.},
    author = {Aleksei Ponomarenko-Timofeev and Olga Galinina and Ravikumar Balakrishnan and Nageen Himayat and Sergey Andreev and Yevgeni Koucheryavy},
    doi = {10.57702/ye0h42cx},
    institution = {No Organization},
    keyword = {'classification', 'federated learning', 'multi-task learning', 'regression'},
    month = {dec},
    publisher = {TIB},
    title = {Multi-Task Learning for Federated Classification and Regression},
    url = {https://service.tib.eu/ldmservice/dataset/multi-task-learning-for-federated-classification-and-regression},
    year = {2024}
}