ONDS: Optimum Node and Data Selection From Constrained IoT for Efficient Online Learning

Supervised Machine Learning (ML) models require large amounts of labeled data for training. However, this becomes challenging when dealing with resource- and network-constrained Internet of Things (IoT) devices that collect data. Furthermore, in scenarios where the acquired data is fast-changing and highly temporal, continuous and online learning becomes necessary. In this paper, we address the problem of efficiently training ML models using data from IoT nodes. We specifically focus on two aspects: i) selecting the nodes that provide data for the re/training, and ii) determining the optimal amounts of data to be acquired from these nodes, considering network and time constraints, while minimizing learning errors. To tackle this optimization problem, we propose ONDS: an Optimum Node and Data Selection algorithm with linear complexity in the worst-case. ONDS offers a model-agnostic solution applicable to different data modalities and ML architectures. To evaluate the performance of ONDS, we conduct experiments using various models and real-world datasets. The results demonstrate the effectiveness of ONDS, as it outperforms existing alternatives in both classification and regression tasks.