Heterogeneous Differential Privacy (HDP) in Federated Learning (FL) allows clients to select individual privacy budgets ($\varepsilon_i$) according to institutional policies and data sensitivity. In practice, many HDP-FL systems employ $\varepsilon$-aware server aggregation to improve model utility by re-weighting client updates according to their declared privacy budgets.
arXiv:2510. 04902v3 Announce Type: replace Abstract: Tuning hyperparameters in federated machine learning can substantially impact model performance.
By Johannes Liebenow, Thorsten Peinemann, Esfandiar Mohammadi
arXiv:2502. 17748v4 Announce Type: replace Abstract: Federated Learning (FL) inherently mitigates mass data centralization risks; however, its privacy protections are not equally distributed - leaving vulnerable individuals disproportionately exposed to sophisticated privacy attacks.
By Tianyu Zhao, Mahmoud Srewa, Salma Elmalaki
arXiv:2608. 15153v1 Announce Type: cross Abstract: Differentially private federated learning must balance privacy protection against model accuracy and training efficiency.
By Wenjing Wei, Alla Jammine, Farid Nait-Abdesselam
arXiv:2606. 04399v1 Announce Type: new Abstract: In the paradigm of decentralized learning, a group of agents collaborate to train a global model using distributed datasets without a central server.
By Yunsheng Yuan, Xue Xiao, Lina Wang, Feng Li
arXiv:2602. 06838v3 Announce Type: replace Abstract: Federated learning enables collaborative model training across distributed clients while preserving data privacy.
By Jin Wang, Hui Ma, Yajun Zhang, Xinjun Pei, Ming Yan, Fei Xing, Yikun Chen