English(EN)Centralized vs Decentralized Federated Learning: A trade-off performance analysis
新研究通过主动客户端选择和隐私分析推进联邦学习
作者PulseAugur 编辑部·[11 个来源]·
研究人员正在探索改进联邦学习的新方法，这是一种在保护隐私的同时跨分布式数据源训练模型的技术。一种名为“明智且私密地选择”的方法，利用互信息和潜在联邦损失，在训练开始前主动选择其数据能最大化效用和公平性的客户端。另一项研究引入了一种轻量级几何信号，通过测量本地训练与全局模型功能行为的偏差来检测异常客户端。此外，新的理论工作为差分隐私联邦学习协议建立了通用下界，并分析了集中式和分布式联邦学习架构之间的权衡。
AI
arXiv:2605.20975v2 Announce Type: replace Abstract: Federated Learning enables collaborative model training across decentralized data sources without data transfer. Averaging-based FL is limited by the presence of non-IID data, which negatively impacts convergence speed and final…
arXiv cs.LG
TIER_1English(EN)·Cristian P\'erez-Corral, Jose I. Mestre, Alberto Fern\'andez-Hern\'andez, Manuel F. Dolz, Enrique S. Quitana-Ort\'i·
arXiv:2605.22266v1 Announce Type: new Abstract: Federated learning enables collaborative training across distributed clients with heterogeneous data, but such heterogeneity often leads to unstable updates and degraded global performance. Moreover, in practical deployments, client…
Federated Learning enables collaborative model training across decentralized data sources without data transfer. Averaging-based FL is limited by the presence of non-IID data, which negatively impacts convergence speed and final model accuracy. Conventional alternatives suffer fr…
We prove a general lower bound for differentially private federated learning protocols with arbitrary public-transcript interactions. The protocol may use any number of adaptive rounds, and each client's local samples may be reused across rounds. For parameter estimation under sq…
We prove a general lower bound for differentially private federated learning protocols with arbitrary public-transcript interactions. The protocol may use any number of adaptive rounds, and each client's local samples may be reused across rounds. For parameter estimation under sq…
Federated Learning (FL) has emerged as a promising paradigm for collaborative model training across distributed edge devices while preserving data privacy especially with the huge increase amount of data due to the adoption of technologies which contributes to the growing number …
arXiv stat.ML
TIER_1English(EN)·Pierre Jobic, Maxime Haddouche, Benjamin Guedj·
arXiv:2310.11203v2 Announce Type: replace-cross Abstract: We introduce a novel strategy to train randomised predictors in federated learning, where each node of the network aims at preserving its privacy by releasing a local predictor but keeping secret its training dataset with …
arXiv stat.ML
TIER_1English(EN)·Konstantinos Ziliaskopoulos, Alexander Vinel·
arXiv:2604.20031v2 Announce Type: replace-cross Abstract: We consider Decision-Focused Federated Learning (DFFL), a predict-then-optimize setting in which multiple clients collaboratively train predictive models for downstream linear optimization problems without exchanging raw d…
arXiv:2605.18656v1 Announce Type: new Abstract: Federated Learning is a leading framework for training ML and AI models collaboratively across numerous user devices or databases. We study the trade-offs among estimation accuracy, privacy constraints, and communication cost for di…
Federated Learning is a leading framework for training ML and AI models collaboratively across numerous user devices or databases. We study the trade-offs among estimation accuracy, privacy constraints, and communication cost for differentially private (DP) federated M estimation…
<h3>What You Need to Know Before Securing Federated Learning Across Clouds</h3><h4><em>Privacy is only the beginning. The harder problem is trust.</em></h4><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*lHXB9t3nJ_YDZWBLCjj-_g.png" /><figcaption>Secure-CCFL ar…
