MALEN

Machine Learning over Networks, Principal Investigator, Swedish Research Council, 2020-2023 (0.5 M€). One of the main characteristics of the IoT and 5-6G technological revolution is the huge data generation. Such wealth of data is forcefully motivating the development of data analysis methods, namely machine learning. Currently, machine learning needs big datasets and very huge computational and communication resources. However, in the fourth technological revolution, data sets of any size will be distributed among several nodes (people, devices, objects, or machines) that might not be able to perform the computations and to share data. Unfortunately, existing machine learning methods are mostly intended for proprietary and high performing networks as in data centres, and would greatly stress communication networks such as IoT and 5-6G wireless networks. In these networks, machine learning methods will encounter new challenges in terms of computation, bandwidth, scalability, privacy, and security. Machine learning over networks face a lack of understanding of the fundamental methods, and poor performance of their algorithms. In this research project, we propose to contribute establishing a new fundamental theory for machine learning over networks.