New federated learning methods tackle privacy, efficiency, and fairness
ByPulseAugur Editorial·[18 sources]·
Researchers are developing new methods for federated learning to improve efficiency, robustness, and privacy. Several papers introduce techniques for handling partial client participation and Byzantine attacks, such as delayed momentum aggregation and server-proximal aggregation. Other work focuses on enhancing privacy through model splitting and differential privacy, or on achieving fairness and personalization by adapting aggregation weights based on client contributions. Additionally, new approaches are exploring one-shot federated learning and optimizing composite federated learning for faster convergence.
AI
IMPACT
These advancements in federated learning could lead to more efficient, secure, and personalized AI models deployed on edge devices.
RANK_REASON
Multiple academic papers published on arXiv detailing novel algorithms and frameworks for federated learning.
arXiv:2303.04345v2 Announce Type: replace Abstract: Federated learning (FL) is a promising framework that models distributed machine learning while protecting the privacy of clients. However, FL suffers performance degradation from heterogeneous and limited data. To alleviate the…
arXiv:2606.02563v1 Announce Type: new Abstract: 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 emp…
arXiv:2606.02172v1 Announce Type: new Abstract: Learning discriminative visual representations from distributed, heterogeneous data is a fundamental challenge in Federated Learning (FL). Prototype-based methods address statistical heterogeneity by sharing class-level representati…
arXiv cs.LG
TIER_1English(EN)·Ivo Osterberg Nilsson, Maximilian Birr Engvall, Viktor Valadi, Teddy Lazebnik·
arXiv:2606.00986v1 Announce Type: new Abstract: Federated learning (FL) enables multiple data holders to train machine learning models collaboratively without centralizing raw data, making it useful in privacy sensitive domains such as healthcare and institutional data sharing. F…
arXiv:2606.01856v1 Announce Type: cross Abstract: Multimodal Federated Learning (MMFL) enables privacy-preserving collaborative learning across decentralized clients with heterogeneous data and modality availability. However, most existing MMFL methods cast multimodal training as…
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 im…
arXiv cs.AI
TIER_1English(EN)·Fabio Turazza, Marco Picone, Marco Mamei·
arXiv:2602.01186v2 Announce Type: replace-cross Abstract: Classical Federated Learning relies on a multi-round iterative process of model exchange and aggregation between server and clients, with high communication costs and privacy risks from repeated model transmissions. In con…
arXiv:2509.02970v3 Announce Type: replace Abstract: Partial participation is essential for communication-efficient federated learning at scale, yet existing Byzantine-robust methods typically assume full client participation. In the partial participation setting, a majority of th…
arXiv:2509.25906v2 Announce Type: replace Abstract: Federated Learning (FL) often adopts differential privacy (DP) to protect client data, but the added noise required for privacy guarantees can substantially degrade model accuracy. To resolve this challenge, we propose model-spl…
arXiv:2601.22274v2 Announce Type: replace Abstract: Real-world federated systems seldom operate on static data: input distributions drift while privacy rules forbid raw-data sharing. We study this setting as Federated Domain-Incremental Learning (FDIL), where (i) clients are hete…
arXiv:2605.30336v1 Announce Type: new Abstract: Federated learning is an emerging distributed paradigm that addresses the challenges posed by heterogeneous, privacy-sensitive data. It enables multiple clients to train a model collaboratively by aggregating their local updates at …
arXiv cs.LG
TIER_1English(EN)·Kun Huang, Shi Pu, Karl Henrik Johansson·
arXiv:2602.03357v2 Announce Type: replace Abstract: This paper proposes FedNMap, a normal map-based method for composite federated learning, where the objective consists of a smooth loss and a possibly nonsmooth regularizer. FedNMap leverages a normal map-based update scheme to h…
Federated learning is an emerging distributed paradigm that addresses the challenges posed by heterogeneous, privacy-sensitive data. It enables multiple clients to train a model collaboratively by aggregating their local updates at a server. However, conventional aggregation sche…
arXiv cs.AI
TIER_1English(EN)·Qiyuan Chen, Xian Wu, Yi Wang, Xianhao Chen·
arXiv:2603.14773v2 Announce Type: replace-cross Abstract: Fine-tuning large models on edge devices is severely hindered by the memory-intensive backpropagation (BP) in standard frameworks like federated learning and split learning. While substituting BP with zeroth-order optimiza…
arXiv:2605.26571v1 Announce Type: new Abstract: Federated learning enables collaborative model training without sharing raw data, but its performance can degrade substantially under heterogeneous client data distributions. A single global model often cannot satisfy diverse client…
Personalized Federated Learning (PFL) constitutes a novel paradigm that tailors Machine Learning (ML) models to individual clients, thereby furnishing personalized model updates whilst upholding stringent data privacy principles. Diverging from conventional standard Federated Lea…
arXiv:2605.29460v1 Announce Type: new Abstract: Federated fine-tuning of foundation models with Low-Rank Adaptation (LoRA) provides an efficient solution for reducing communication and computation costs while preserving data locality. However, the direct combination of FedAvg and…
arXiv cs.CV
TIER_1English(EN)·Md. Arifur Rahman, Isha Das, Mushfiqur Rahman Abir, B. M. Taslimul Haque, Abdullah Al Noman, Abir Ahmed, Md. Jakir Hossen·