Decentralised and collaborative machine learning framework for IoT
This work addresses security and efficiency issues for IoT deployments with resource-constrained devices, but it appears incremental as it builds on existing decentralized learning concepts.
The authors tackled the problem of security and resource constraints in IoT by proposing a decentralized and collaborative machine learning framework, achieving promising results in accuracy, training time, and robustness compared to a centralized approach.
Decentralised machine learning has recently been proposed as a potential solution to the security issues of the canonical federated learning approach. In this paper, we propose a decentralised and collaborative machine learning framework specially oriented to resource-constrained devices, usual in IoT deployments. With this aim we propose the following construction blocks. First, an incremental learning algorithm based on prototypes that was specifically implemented to work in low-performance computing elements. Second, two random-based protocols to exchange the local models among the computing elements in the network. Finally, two algorithmics approaches for prediction and prototype creation. This proposal was compared to a typical centralized incremental learning approach in terms of accuracy, training time and robustness with very promising results.