EdgeConvEns: Convolutional Ensemble Learning for Edge Intelligence
This work addresses the problem of efficient and private deep learning for edge intelligence applications, offering an incremental improvement over existing decentralized methods like federated learning.
The paper tackles the challenge of deploying deep learning on edge devices with limited computational power and privacy constraints by proposing EdgeConvEns, a convolutional ensemble learning approach that trains heterogeneous weak models on edge devices and ensembles them centrally, achieving state-of-the-art performance with fewer communications and less data.
Deep edge intelligence aims to deploy deep learning models that demand computationally expensive training in the edge network with limited computational power. Moreover, many deep edge intelligence applications require handling distributed data that cannot be transferred to a central server due to privacy concerns. Decentralized learning methods, such as federated learning, offer solutions where models are learned collectively by exchanging learned weights. However, they often require complex models that edge devices may not handle and multiple rounds of network communication to achieve state-of-the-art performances. This study proposes a convolutional ensemble learning approach, coined EdgeConvEns, that facilitates training heterogeneous weak models on edge and learning to ensemble them where data on edge are heterogeneously distributed. Edge models are implemented and trained independently on Field-Programmable Gate Array (FPGA) devices with various computational capacities. Learned data representations are transferred to a central server where the ensemble model is trained with the learned features received from the edge devices to boost the overall prediction performance. Extensive experiments demonstrate that the EdgeConvEns can outperform the state-of-the-art performance with fewer communications and less data in various training scenarios.