Optimizing Federated Learning With Aggregation Strategies: A Comprehensive Survey

doi:10.1109/OJCS.2025.3590102

Optimizing Federated Learning With Aggregation Strategies: A Comprehensive Survey

2025-01-01

0

OA

AI

Yasar Abbas Ur Rehman

DOI：10.1109/OJCS.2025.3590102

Original

Original request for help

Save

Abstract

En 中文

This article provides a comprehensive survey of aggregation strategies in federated learning (FL). This decentralized machine learning (ML) paradigm enables multiple clients to collaboratively train models without sharing their local datasets. Aggregation is a pivotal aspect of FL, as it integrates model updates from diverse clients into a unified global model while addressing critical challenges such as data heterogeneity, scalability, and privacy preservation. The study categorizes aggregation strategies into three primary approaches: data-centric, model-centric, and secure aggregation, each tailored to address distinct problems in FL systems. Data-centric strategies focus on addressing non-independent and identically distributed (non-IID) data across clients, ensuring that model updates account for imbalances in data distributions. Model-centric strategies optimize the aggregation of model parameters, emphasizing techniques such as weighted averaging and model distillation to improve model performance across clients with diverse data characteristics. Secure aggregation techniques aim to enhance privacy and robustness, protecting client data from potential adversarial threats through encryption-based methods like secure multi-party computation (SMPC) and Byzantine-resilient techniques. The analysis delves into the advantages and limitations of these aggregation strategies, particularly their role in tackling challenges like non-IID data, communication efficiency, and resistance to adversarial attacks. Furthermore, the article identifies existing research gaps in FL, including the need for more scalable and robust aggregation methods capable of reducing communication costs, enhancing privacy guarantees, and improving performance in highly heterogeneous environments. These insights provide a roadmap for future research aimed at advancing aggregation strategies in FL to improve model accuracy, security, and efficiency in real-world applications.

Keywords:

Federated learning

aggregation strategies

weighted averaging

model distillation

data heterogeneity

Byzantine-resilient aggregation

privacy preservation

communication efficiency

non-IID data

secure aggregation

Optimizing Federated Learning With Aggregation Strategies: A Comprehensive Survey

Abstract

Journal

Organization