XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning

doi:doi:10.57702/la3nk1xo

XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning

User-generated data distributions are often imbalanced across devices and labels, hampering the performance of federated learning (FL). To remedy to this non-independent and identically distributed (non-IID) data problem, in this work we develop a privacy-preserving XOR based mixup data augmentation technique, coined XorMixup, and thereby propose a novel one-shot FL framework, termed XorMixFL.

BibTex:

@dataset{MyungJae_Shin_and_Chihoon_Hwang_and_Joongheon_Kim_and_Jihong_Park_and_Mehdi_Bennis_and_Seong-Lyun_Kim_2024,
    abstract = {User-generated data distributions are often imbalanced across devices and labels, hampering the performance of federated learning (FL). To remedy to this non-independent and identically distributed (non-IID) data problem, in this work we develop a privacy-preserving XOR based mixup data augmentation technique, coined XorMixup, and thereby propose a novel one-shot FL framework, termed XorMixFL.},
    author = {MyungJae Shin and Chihoon Hwang and Joongheon Kim and Jihong Park and Mehdi Bennis and Seong-Lyun Kim},
    doi = {10.57702/la3nk1xo},
    institution = {No Organization},
    keyword = {'Data Augmentation', 'Federated Learning', 'Privacy-Preserving', 'XorMixFL', 'XorMixup'},
    month = {dec},
    publisher = {TIB},
    title = {XOR Mixup: Privacy-Preserving Data Augmentation for One-Shot Federated Learning},
    url = {https://service.tib.eu/ldmservice/dataset/xor-mixup--privacy-preserving-data-augmentation-for-one-shot-federated-learning},
    year = {2024}
}