2026年8月在arXiv上发表的多篇研究论文介绍了增强联邦学习（FL）和去中心化FL的新方法。这些方法解决了多模态FL中的模态缺失（Flux）、非凸复合优化（DEPOSITUM）、对抗隐形攻击者的鲁棒声誉机制（R2CFL）、用于收敛的自适应层级学习率（FedA2L）、平衡数据质量和数量（FedTVD）、非IID数据的基于损失的加权（FedLBW）、绕过聚合防御（Krum-Proxy攻击）、子模型FL中的容量分配（HAS-FL）、基于信任的激励机制（半去中心化FL）以及通过方差感知非参数经验贝叶斯（VANEB）进行个性化FL等挑战。
AI
arXiv:2608.12108v1 Announce Type: new Abstract: Federated learning (FL) enables collaborative model training across distributed clients while keeping data local. A central challenge is determining which client updates are beneficial for aggregation with respect to each client's t…
arXiv cs.AI
TIER_1English(EN)·Gabriele D'Acunto, Enrico Grimaldi, Valeria Avino, Mario Edoardo Pandolfo, Leonardo Di Nino, Sergio Barbarossa, Paolo Di Lorenzo·
arXiv:2608.10016v1 Announce Type: cross Abstract: Heterogeneous federated systems require agents to learn and exchange informative representations despite differences in data distributions, sensing modalities, model architectures, latent dimensionalities, and local learning objec…
arXiv:2608.09221v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative model training across distributed client devices while preserving data privacy. However, FL faces significant challenges due to data heterogeneity, particularly in terms of label distr…
arXiv:2608.09208v1 Announce Type: cross Abstract: Decentralized intelligence systems with heterogeneous devices and limited coordination increasingly rely on decentralized federated learning (DFL). However, DFL suffers from convergence inefficiency under data heterogeneity due to…
arXiv:2608.09240v1 Announce Type: cross Abstract: Multimodal federated learning (FL) supports collaborative modeling in privacy-sensitive health-sensing and medical settings, but realistic deployments often exhibit dual-axis modality missingness: clients have different modality s…
arXiv:2608.08574v1 Announce Type: new Abstract: Crowdsourced Federated Learning (CrowdFL) extends traditional federated learning by enabling open and heterogeneous participation through a crowdsourcing paradigm. In this setting, reputation-driven incentive mechanisms are commonly…
arXiv:2504.12742v2 Announce Type: replace Abstract: Decentralized Federated Learning (DFL) enables collaborative model training without relying on a central server. When local objectives are nonconvex and coupled with nonsmooth weakly convex regularization, DFL gives rise to a ch…
arXiv cs.AI
TIER_1English(EN)·Srinivasan Subramanian, Md. Abdullah Al Hafiz Khan, Kazi Aminul Islam·
arXiv:2608.06637v1 Announce Type: cross Abstract: Robust aggregation methods are widely used in federated learning to mitigate the impact of adversarial client behavior. Distance-based aggregation rules, such as Krum and Multi-Krum, select updates that are closest to the majority…
arXiv:2608.07007v1 Announce Type: new Abstract: Federated Learning (FL) enables collaborative machine learning (ML) across distributed clients while preserving privacy. However, efficient model convergence in FL remains challenging, especially in wireless networks where non-indep…
arXiv:2608.07157v1 Announce Type: new Abstract: Sub-model federated learning lets resource-constrained clients train width-reduced versions of a global model, but existing methods allocate capacity by device resources alone. A natural next step, allocating capacity by each client…
arXiv cs.MA (Multiagent)
TIER_1English(EN)·Paolo Di Lorenzo·
Heterogeneous federated systems require agents to learn and exchange informative representations despite differences in data distributions, sensing modalities, model architectures, latent dimensionalities, and local learning objectives. To address this challenge, we propose Sheaf…
arXiv:2602.08290v2 Announce Type: replace-cross Abstract: In federated learning (FL), decentralized model training allows multi-ple participants to collaboratively improve a shared machine learning model without exchanging raw data. However, ensuring the integrity and reliability…
arXiv stat.ML
TIER_1English(EN)·Jae Ho Chang, Arnab Auddy, Subhadeep Paul·
arXiv:2608.09074v1 Announce Type: new Abstract: We develop a new approach to Personalized Federated Learning across heterogeneous clients using Nonparametric Empirical Bayes (NPEB). Leveraging the asymptotic normality of local parameter estimates obtained from Empirical Risk Mini…
<p>Federated learning trains a shared model across many devices without collecting their data on a server. That is a real and useful property. It is also routinely stated as though it were three properties, and the other two — that the server learns nothing about individuals, and…
