Reviewing Federated Learning Aggregation Algorithms; Strategies, Contributions, Limitations and Future Perspectives

Abstract

The success of machine learning (ML) techniques in the formerly difficult areas of data analysis and pattern extraction has led to their widespread incorporation into various aspects of human life. This success is due in part to the increasing computational power of computers and in part to the improved ability of ML algorithms to process large amounts of data in various forms. Despite these improvements, certain issues, such as privacy, continue to hinder the development of this field. In this context, a privacy-preserving, distributed, and collaborative machine learning technique called federated learning (FL) has emerged. The core idea of this technique is that, unlike traditional machine learning, user data is not collected on a central server. Nevertheless, models are sent to clients to be trained locally, and then only the models themselves, without associated data, are sent back to the server to combine the different locally trained models into a single global model. In this respect, the aggregation algorithms play a crucial role in the federated learning process, as they are responsible for integrating the knowledge of the participating clients, by integrating the locally trained models to train a global one. To this end, this paper explores and investigates several federated learning aggregation strategies and algorithms. At the beginning, a brief summary of federated learning is given so that the context of an aggregation algorithm within a FL system can be understood. This is followed by an explanation of aggregation strategies and a discussion of current aggregation algorithms implementations, highlighting the unique value that each brings to the knowledge. Finally, limitations and possible future directions are described to help future researchers determine the best place to begin their own investigations.

Exploring the Synergy of Fog Computing, Blockchain, and Federated Learning for IoT Applications: A Systematic Literature Review

“…The task of Local Data Management involves overseeing proper data handling and secure storage on individual devices. Meanwhile, the Local Learning Models, which are trained using local data, undergo continuous refinement through updates throughout the FL process [10], [17], [36]. 2) Network Layer: This layer manages interactions among devices, nodes, local servers, and aggregation servers within the FL system.…”

“…2) Network Layer: This layer manages interactions among devices, nodes, local servers, and aggregation servers within the FL system. It uses advanced Channel Coding techniques to robust data transmission over potentially noisy channels, supported by various Communication Protocols (e.g., 6G, 5G, Z-Wave, ZigBee, Wi-Fi) to facilitate data exchange [17], [36], [37]. Global Updates drive the continual refinement of the overarching model [10], [17], [36], [37].…”

“…It uses advanced Channel Coding techniques to robust data transmission over potentially noisy channels, supported by various Communication Protocols (e.g., 6G, 5G, Z-Wave, ZigBee, Wi-Fi) to facilitate data exchange [17], [36], [37]. Global Updates drive the continual refinement of the overarching model [10], [17], [36], [37]. 4) Application Layer: Positioned as the uppermost layer, this layer customizes the global model to align with specific applications through Model Customization.…”

“…3) Architecture Layers. Considering that IoT applications are commonly presented in Layered architectures, this sub-extraction criteria provides a list of layers that can be utilized, and are common, in IoT applications when integrating FC-BC-FL (See Figure 7) [12], [36], [39].…”

“…FL Aggregation. Aggregation is the merging of local model updates from multiple devices to create a global model while preserving data privacy [10], [36]. This criterion helps in identifying important FL aggregation facts (see Figure 10).…”