Cover Image

A Fast and Flat Federated Learning Method via Weighted Momentum and Sharpness-Aware Minimization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Tianle, Huang, Yongzhi, Jiang, Linshan, Liu, Chang, Xie, Qipeng, Du, Wenfeng, Wang, Lu, Wu, Kaishun
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Taming Request Imbalance: SLO-Aware Scheduling for Disaggregated LLM Inference
by: Wang, Qipeng
Published: (2026)

FWeb3: A Practical Incentive-Aware Federated Learning Framework
by: Yan, Peishen, et al.
Published: (2026)

OFL-W3: A One-shot Federated Learning System on Web 3.0
by: Jiang, Linshan, et al.
Published: (2024)

Hypernetworks for Model-Heterogeneous Personalized Federated Learning
by: Zhang, Chen, et al.
Published: (2025)

Ghidorah: Fast LLM Inference on Edge with Speculative Decoding and Hetero-Core Parallelism
by: Wei, Jinhui, et al.
Published: (2025)

Accelerating Biclique Counting on GPU
by: Qiu, Linshan, et al.
Published: (2024)

Heterogeneity-Aware Memory Efficient Federated Learning via Progressive Layer Freezing
by: Yebo, Wu, et al.
Published: (2024)

Decentralized Semantic Federated Learning for Real-Time Public Safety Tasks: Challenges, Methods, and Directions
by: Li, Baosheng, et al.
Published: (2025)

ECC-SNN: Cost-Effective Edge-Cloud Collaboration for Spiking Neural Networks
by: Yu, Di, et al.
Published: (2025)

Lancelot: Towards Efficient and Privacy-Preserving Byzantine-Robust Federated Learning within Fully Homomorphic Encryption
by: Jiang, Siyang, et al.
Published: (2024)

A Structure-Aware Irregular Blocking Method for Sparse LU Factorization
by: Hu, Zhen, et al.
Published: (2025)

Cabinet: Dynamically Weighted Consensus Made Fast
by: Zhang, Gengrui, et al.
Published: (2025)

Locally Estimated Global Perturbations are Better than Local Perturbations for Federated Sharpness-aware Minimization
by: Fan, Ziqing, et al.
Published: (2024)

Age-Aware Partial Gradient Update Strategy for Federated Learning Over the Air
by: Du, Ruihao, et al.
Published: (2025)

Dynamic Regularized Sharpness Aware Minimization in Federated Learning: Approaching Global Consistency and Smooth Landscape
by: Sun, Yan, et al.
Published: (2023)

Bandwidth-Aware and Overlap-Weighted Compression for Communication-Efficient Federated Learning
by: Tang, Zichen, et al.
Published: (2024)

GPU-Accelerated Batch-Dynamic Subgraph Matching
by: Qiu, Linshan, et al.
Published: (2024)

A Survey on Model-heterogeneous Federated Learning: Problems, Methods, and Prospects
by: Fan, Boyu, et al.
Published: (2023)

Efficient Pre-Training of LLMs via Topology-Aware Communication Alignment on More Than 9600 GPUs
by: He, Guoliang, et al.
Published: (2025)

Lion: Minimizing Distributed Transactions through Adaptive Replica Provision (Extended Version)
by: Zheng, Qiushi, et al.
Published: (2024)

The Complexity of Distributed Minimum Weight Cycle Approximation
by: Chang, Yi-Jun, et al.
Published: (2026)

Pollen: High-throughput Federated Learning Simulation via Resource-Aware Client Placement
by: Sani, Lorenzo, et al.
Published: (2023)

DP$^2$-FedSAM: Enhancing Differentially Private Federated Learning Through Personalized Sharpness-Aware Minimization
by: Zhang, Zhenxiao, et al.
Published: (2024)

FedCostAware: Enabling Cost-Aware Federated Learning on the Cloud
by: Sinha, Aditya, et al.
Published: (2025)

Ringmaster LMO: Asynchronous Linear Minimization Oracle Momentum Method
by: Sadiev, Abdurakhmon, et al.
Published: (2026)

Inference Load-Aware Orchestration for Hierarchical Federated Learning
by: Lackinger, Anna, et al.
Published: (2024)

SuperSFL: Resource-Heterogeneous Federated Split Learning with Weight-Sharing Super-Networks
by: Asif, Abdullah Al, et al.
Published: (2026)

HexAGenT: Efficient Agentic LLM Serving via Workflow- and Heterogeneity-Aware Scheduling
by: Peng, You, et al.
Published: (2026)

Data Heterogeneity-Aware Client Selection for Federated Learning in Wireless Networks
by: Yang, Yanbing, et al.
Published: (2025)

FedFog: Resource-Aware Federated Learning in Edge and Fog Networks
by: Sobati-M, Somayeh
Published: (2025)

Ordered Momentum for Asynchronous SGD
by: Shi, Chang-Wei, et al.
Published: (2024)

FlexFL: Heterogeneous Federated Learning via APoZ-Guided Flexible Pruning in Uncertain Scenarios
by: Chen, Zekai, et al.
Published: (2024)

Minimizing Intellectual Property Risks via Self-Stabilizing Algorithms
by: Kennedy, Ken, et al.
Published: (2026)

pdGRASS: A Fast Parallel Density-Aware Algorithm for Graph Spectral Sparsification
by: Zhao, Tiancheng, et al.
Published: (2025)

ClusterLess: Deadline-Aware Serverless Workflow Orchestration on Federated Edge Clusters
by: Farahani, Reza, et al.
Published: (2026)

FedUHB: Accelerating Federated Unlearning via Polyak Heavy Ball Method
by: Jiang, Yu, et al.
Published: (2024)

Fast Topology-Aware Lossy Data Compression with Full Preservation of Critical Points and Local Order
by: Fallin, Alex, et al.
Published: (2026)

Twinning for Space-Air-Ground-Sea Integrated Networks: Beyond Conventional Digital Twin Towards Goal-Oriented Semantic Twin
by: Qiu, Yifei, et al.
Published: (2025)

Harpagon: Minimizing DNN Serving Cost via Efficient Dispatching, Scheduling and Splitting
by: Zhao, Zhixin, et al.
Published: (2024)

SAFL: Structure-Aware Personalized Federated Learning via Client-Specific Clustering and SCSI-Guided Model Pruning
by: Li, Nan, et al.
Published: (2025)