Image de couverture de livre

Local Gradient Regulation Stabilizes Federated Learning under Client Heterogeneity

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Luo, Ping, Wang, Jiahuan, Wen, Ziqing, Sun, Tao, Li, Dongsheng
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Distributed, Parallel, and Cluster Computing
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Accelerating Federated Learning by Selecting Beneficial Herd of Local Gradients
par: Luo, Ping, et autres
Publié: (2024)

Achieving Linear Speedup in Asynchronous Federated Learning with Heterogeneous Clients
par: Wang, Xiaolu, et autres
Publié: (2024)

Heterogeneity-Aware Client Selection Methodology For Efficient Federated Learning
par: Balivada, Nihal, et autres
Publié: (2026)

Fed-pilot: Optimizing LoRA Allocation for Efficient Federated Fine-Tuning with Heterogeneous Clients
par: Zhang, Zikai, et autres
Publié: (2024)

Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis
par: Crawshaw, Michael, et autres
Publié: (2024)

Federated Graph Learning with Graphless Clients
par: Fu, Xingbo, et autres
Publié: (2024)

FedGCS: A Generative Framework for Efficient Client Selection in Federated Learning via Gradient-based Optimization
par: Ning, Zhiyuan, et autres
Publié: (2024)

Towards Client Driven Federated Learning
par: Li, Songze, et autres
Publié: (2024)

Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable
par: Ying, Bicheng, et autres
Publié: (2025)

Debiasing Federated Learning with Correlated Client Participation
par: Sun, Zhenyu, et autres
Publié: (2024)

FedHFT: Efficient Federated Finetuning with Heterogeneous Edge Clients
par: Ilhan, Fatih, et autres
Publié: (2025)

CHASe: Client Heterogeneity-Aware Data Selection for Effective Federated Active Learning
par: Zhang, Jun, et autres
Publié: (2025)

GPFL: A Gradient Projection-Based Client Selection Framework for Efficient Federated Learning
par: Na, Shijie, et autres
Publié: (2024)

Federated Learning under Partially Class-Disjoint Data via Manifold Reshaping
par: Fan, Ziqing, et autres
Publié: (2024)

A Joint Approach to Local Updating and Gradient Compression for Efficient Asynchronous Federated Learning
par: Song, Jiajun, et autres
Publié: (2024)

Beyond Aggregation: Guiding Clients in Heterogeneous Federated Learning
par: Wang, Zijian, et autres
Publié: (2025)

Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients
par: Ma, Mengmeng, et autres
Publié: (2024)

Towards Seamless Hierarchical Federated Learning under Intermittent Client Participation: A Stagewise Decision-Making Methodology
par: Wu, Minghong, et autres
Publié: (2025)

Adaptive Client Selection via Q-Learning-based Whittle Index in Wireless Federated Learning
par: Li, Qiyue, et autres
Publié: (2025)

FedEve: On Bridging the Client Drift and Period Drift for Cross-device Federated Learning
par: Shen, Tao, et autres
Publié: (2025)

FedAR: Addressing Client Unavailability in Federated Learning with Local Update Approximation and Rectification
par: Jiang, Chutian, et autres
Publié: (2024)

Ranking-based Client Selection with Imitation Learning for Efficient Federated Learning
par: Tian, Chunlin, et autres
Publié: (2024)

MimiC: Combating Client Dropouts in Federated Learning by Mimicking Central Updates
par: Sun, Yuchang, et autres
Publié: (2023)

Federated Learning in the Presence of Adversarial Client Unavailability
par: Su, Lili, et autres
Publié: (2023)

FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices using a Computing Power Aware Scheduler
par: Li, Zilinghan, et autres
Publié: (2023)

FedMOA: Federated GRPO for Personalized Reasoning LLMs under Heterogeneous Rewards
par: Wang, Ziyao, et autres
Publié: (2026)

Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning
par: Fenoglio, Dario, et autres
Publié: (2024)

Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization
par: Fan, Ziqing, et autres
Publié: (2024)

Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients
par: Zuo, Shiyuan, et autres
Publié: (2024)

FedAdaVR: Adaptive Variance Reduction for Robust Federated Learning under Limited Client Participation
par: Howlader, S M Ruhul Kabir, et autres
Publié: (2026)

The Diversity Bonus: Learning from Dissimilar Distributed Clients in Personalized Federated Learning
par: Wu, Xinghao, et autres
Publié: (2024)

Communication-Efficient Multimodal Federated Learning: Joint Modality and Client Selection
par: Yuan, Liangqi, et autres
Publié: (2024)

Robust Model Aggregation for Heterogeneous Federated Learning: Analysis and Optimizations
par: Shao, Yumeng, et autres
Publié: (2024)

Hypernetworks for Model-Heterogeneous Personalized Federated Learning
par: Zhang, Chen, et autres
Publié: (2025)

Emulating Full Participation: An Effective and Fair Client Selection Strategy for Federated Learning
par: Li, Qingming, et autres
Publié: (2024)

Greedy Shapley Client Selection for Communication-Efficient Federated Learning
par: Singhal, Pranava, et autres
Publié: (2023)

Maverick-Aware Shapley Valuation for Client Selection in Federated Learning
par: Yang, Mengwei, et autres
Publié: (2024)

Harnessing Increased Client Participation with Cohort-Parallel Federated Learning
par: Dhasade, Akash, et autres
Publié: (2024)

Adaptive Client Selection with Personalization for Communication Efficient Federated Learning
par: de Souza, Allan M., et autres
Publié: (2024)

Federated Model Heterogeneous Matryoshka Representation Learning
par: Yi, Liping, et autres
Publié: (2024)