The increasing demand for distributed machine learning like Federated Learning (FL) in dynamic, resource-constrained edge environments, 5G/6G networks, and the proliferation of mobile and edge devices, presents significant challenges related to fault tolerance, elasticity, and communication efficiency. This paper addresses these issues by proposing a novel modular and resilient FL framework. In this context, resilience refers to the system’s ability to maintain operation and performance despite disruptions. The framework is built on decoupled modules handling core FL functionalities, allowing flexibility in integrating various algorithms, communication protocols, and resilience strategies. Results demonstrate the framework’s ability to integrate different communication protocols and FL paradigms, showing that protocol choice significantly impacts performance, particularly in high-volume communication scenarios, with Zenoh and MQTT exhibiting lower overhead than Kafka in tested configurations, and Zenoh emerging as the most efficient communication option. Additionally, the framework successfully maintained model training and achieved convergence even when simulating probabilistic worker failures, achieving a MCC of 0.9453.

The technological world has grown by incorporating billions of small sensing devices, collecting and sharing large amounts of diversified data over the new generation of wireless and mobile networks. We can use semantic similarity models to help organize and optimize these devices. Even so, many of the proposed semantic similarity models do not consider the constrained and dynamic environments where these devices are present (IoT, edge computing, 5g, and next-generation networks). In this paper, we review the commonly used models, discuss the limitations of our previous model, and explore latent space methods (through matrix factorization) to reduce noise and correct the model profiles with no additional data. The new proposal is evaluated with corpus-based state-of-the-art approaches achieving competitive results while having four times faster training time than the next fastest model and occupying 36 times less disk space than the next smallest model.

The rise of the Internet of Things (IoT) has led to an exponential increase in data generated by connected devices. Machine Learning (ML) has emerged as a powerful tool to analyze these data and enable intelligent IoT applications. However, developing and managing ML applications in the decentralized Cloud-to-Things continuum is extremely complex. This paper proposes Zenoh-Flow, a dataflow programming framework that supports the implementation of End-to-End (E2E) ML pipelines in a fully decentralized manner and abstracted from communication aspects. Thus, it simplifies the development and upgrade process of the next-generation ML-powered applications in the IoT domain. The proposed framework was demonstrated using a real-world use case, and the results showcased a significant improvement in overall performance and network usage compared to the original implementation. Additionally, other of its inherent benefits are a significant step towards developing efficient and scalable ML applications in the decentralized IoT ecosystem.