新框架增强联邦学习的隐私、鲁棒性和效率 · 跟踪4个来源

报道来源 [4]

1. arXiv cs.AI TIER_1 English(EN) · Harsh Kasyap, Anil Kumar Pradhan, Ugur Ilker Atmaca, Graham Cormode, Carsten Maple · 2026-07-09 04:00

   PRoVeFL: Private Robust and Verifiable Aggregation in Federated Learning

   arXiv:2607.06612v1 Announce Type: cross Abstract: Federated Learning (FL) enables multiple clients to collaboratively train machine learning models while retaining data locality, thereby enhancing user privacy. However, traditional FL frameworks rely on a centralized aggregation …

2. arXiv cs.AI TIER_1 English(EN) · Jin Wang, Hui Ma, Yajun Zhang, Xinjun Pei, Ming Yan, Fei Xing, Yikun Chen · 2026-07-09 04:00

   An Adaptive Differentially Private Federated Learning Framework

   arXiv:2602.06838v3 Announce Type: replace Abstract: Federated learning enables collaborative model training across distributed clients while preserving data privacy. However, in practical deployments, device heterogeneity and non-independent and identically distributed (Non-IID) …

3. arXiv cs.LG TIER_1 English(EN) · Dhruv Garg, Neha Lakhani, Debopam Sanyal, Myungjin Lee, Alexey Tumanov, Ada Gavrilovska · 2026-07-09 04:00

   Robust Federated Learning Under Real-World Client Churn

   arXiv:2607.06979v1 Announce Type: new Abstract: Federated Learning (FL) enables training shared models on private, on-device data, but production deployments remain constrained to slow, multi-day refresh cycles due to the complexity of coordinating massive client populations. For…

4. arXiv cs.LG TIER_1 English(EN) · T. Tony Cai, Yicheng Li · 2026-07-09 04:00

   A Van Trees Lower Bound for Fully Interactive Differentially Private Federated Learning

   arXiv:2605.19813v2 Announce Type: replace Abstract: Federated differentially private protocols can communicate over many adaptive rounds and reuse each client's local samples. Existing lower bound arguments for federated DP are often restricted to noninteractive protocols or fres…