Distributed Treansfer Learning in B5G Industrial Networks
IEEE Transactions on Industrial InformaticsIn this paper, we propose a lightweight blockchain inspired framework - Magnum - as a magazine of transfer learning models in blocks. We propose the storage of these blocks on proximal fog nodes to simplify access to pre-trained base models by industrial plants to tune them before deployment. We design Magnum for B5G-enabled scenarios to reduce the block transfer time. We formulate a demand-centric distribution scheme to further reduce search and access time by adopting a Nonlinear Program model and solving it using the branch and bound method. Through extensive experiments and comparison with state-of-the-art solutions, we show that Magnum retains the accuracy of the models and present its feasibility with a maximum CPU and memory usage of 80% and 6%, respectively. Additionally, while Magnum requires a maximum of 10 seconds for writing models as large as 17 Mb on the blocks, it requires 16 micro-seconds for fetching the same.
Read More PDF