Efficient Training Convolutional Neural Networks on Edge Devices with Gradient-pruned Sign-symmetric Feedback Alignment
This work addresses energy efficiency challenges for edge device training in distributed learning, representing an incremental improvement over prior methods.
The paper tackles the problem of limited training capability on edge devices in distributed learning by proposing a novel approach that exploits redundancy and weight asymmetry in backpropagation, resulting in a 5x improvement in energy efficiency with negligible accuracy loss.
With the prosperity of mobile devices, the distributed learning approach enabling model training with decentralized data has attracted wide research. However, the lack of training capability for edge devices significantly limits the energy efficiency of distributed learning in real life. This paper describes a novel approach of training DNNs exploiting the redundancy and the weight asymmetry potential of conventional backpropagation. We demonstrate that with negligible classification accuracy loss, the proposed approach outperforms the prior arts by 5x in terms of energy efficiency.