In order to reduce the performance of the federated learning model caused by data heterogeneity in traffic flow prediction, this paper proposes an improved G-FedProx framework, and combines the real-time traffic status, weather and holiday data obtained by Amap Application Programming Interface (API)...

From centralized learning to distributed learning, data encountered a explosive growth. As distributed learning became very popular in a large number of areas, people began to care about the privacy issue. In order to dispel people’s concerns, federated learning was introduced. By the idea of “models...

This study focuses on deep subspace clustering in a federated learning framework, aiming to address the challenge of clustering high-dimensional data with privacy protection in a distributed environment. Traditional deep clustering methods usually have difficulty dealing with complex data scenarios and...

With the increasing scale of large model training, the traditional centralized training model faces serious challenges in terms of data privacy, communication efficiency and device heterogeneity. The data privacy problem stems from the inability to centrally store sensitive information (e.g., in the...

Federated learning has emerged as a promising solution to address the critical challenges of privacy protection and communication efficiency in distributed data processing, particularly within the contexts of edge computing and Internet of Things environments. This study explores Local SGD as the primary...

With large-scale rollout of Internet of Things (IoT) appliances, the data at the network edge has expanded exponentially. Conventional centralized learning techniques face challenges such as exposure of privacy and delayed response when dealing with this data. Federated learning, being a decentralized...

The growing depth of a machine learning model and scale of data volume necessitate to use distributed training system instead of the capacity of single machine. Herein, this paper presents a thorough treatment of two key architectural paradigms – the parameter server and decentralized architectures –...

In the current digital era, the growing demand for personalized usage environments has increased the volume and diversity of data used in distributed machine learning, pushing the data computing and storage capabilities to their limit. Thus, numerous parallel optimization strategies emerge to enhance...

As the core power unit of modern industrial equipment, such as new energy vehicles, the fault diagnosis of the electric drive system is very important to the safety and reliability of the equipment. However, the traditional fault diagnosis methods lack stability, and the centralized model also has many...

With the increasing development of smart cities, large amounts of video data from surveillance systems pose significant challenges in terms of real-time processing, privacy protection, and efficient multi-camera collaboration. In the context of intelligent transportation systems, achieving accurate vehicle...

This paper provides a comprehensive and in-depth review of federated learning technology, systematically elaborating on its theoretical foundation, technical implementation, application scenarios, and development trajectory. Firstly, it constructs a theoretical framework for federated learning from three...

This study examines the diffusion of agricultural technology innovations within a small-world network context, constructing a cognitive utility threshold model. Key findings indicate that technology performance significantly impacts the diffusion of agricultural innovations. Farmers’ cognitive utility...