Enabling federated learning across the computing continuum: Systems, challenges and future directions
In recent years, as the boundaries of computing have expanded with the emergence of the
Internet of Things (IoT) and its increasing number of devices continuously producing flows of …
Internet of Things (IoT) and its increasing number of devices continuously producing flows of …
A review of client selection methods in federated learning
S Mayhoub, T M. Shami - Archives of Computational Methods in …, 2024 - Springer
Federated learning (FL) is a promising new technology that allows machine learning (ML)
models to be trained locally on edge devices while preserving the privacy of the devices' …
models to be trained locally on edge devices while preserving the privacy of the devices' …
Collaborative policy learning for dynamic scheduling tasks in cloud-edge-terminal IoT networks using federated reinforcement learning
In this article, we examine cloud–edge–terminal Internet of Things (IoT) networks, where
edges undertake a range of typical dynamic scheduling tasks. In these IoT networks, a …
edges undertake a range of typical dynamic scheduling tasks. In these IoT networks, a …
Mimic: Combating client dropouts in federated learning by mimicking central updates
Federated learning (FL) is a promising framework for privacy-preserving collaborative
learning, where model training tasks are distributed to clients and only the model updates …
learning, where model training tasks are distributed to clients and only the model updates …
A Comprehensive Overview of IoT-Based Federated Learning: Focusing on Client Selection Methods
The integration of the Internet of Things (IoT) with machine learning (ML) is revolutionizing
how services and applications impact our daily lives. In traditional ML methods, data are …
how services and applications impact our daily lives. In traditional ML methods, data are …
Efficient client selection based on contextual combinatorial multi-arm bandits
To overcome the challenge of limited bandwidth, client selection has been considered an
effective method for optimizing Federated Learning (FL). However, since the volatility of the …
effective method for optimizing Federated Learning (FL). However, since the volatility of the …
The analysis and optimization of volatile clients in over-the-air federated learning
This paper investigates the implementation of Federated Learning (FL) in an over-the-air
computation system with volatile clients, where each client operates under a limited energy …
computation system with volatile clients, where each client operates under a limited energy …
A systematic literature review on client selection in federated learning
C Smestad, J Li - Proceedings of the 27th International Conference on …, 2023 - dl.acm.org
With the arising concerns of privacy within machine learning, federated learning (FL) was
invented in 2017, in which the clients, such as mobile devices, train a model and send the …
invented in 2017, in which the clients, such as mobile devices, train a model and send the …
Integrating Explainable AI with Federated Learning for Next-Generation IoT: A comprehensive review and prospective insights
The emergence of the Internet of Things (IoT) signifies a transformative wave of innovation,
establishing a network of devices designed to enrich everyday experiences. Developing …
establishing a network of devices designed to enrich everyday experiences. Developing …
A multifaceted survey on federated learning: Fundamentals, paradigm shifts, practical issues, recent developments, partnerships, trade-offs, trustworthiness, and ways …
A Majeed, SO Hwang - IEEE Access, 2024 - ieeexplore.ieee.org
Federated learning (FL) is considered a de facto standard for privacy preservation in AI
environments because it does not require data to be aggregated in some central place to …
environments because it does not require data to be aggregated in some central place to …