Deep Partial Updating: Towards Communication Efficient Updating for On-device Inference
This addresses the challenge of constrained communication resources in edge intelligence applications, enabling efficient server-to-edge updates for on-device inference.
The paper tackles the problem of communication-efficient updating of deep neural networks on edge devices by proposing a weight-wise deep partial updating paradigm that selects a small subset of weights to update, achieving similar performance to full updating with reduced communication overhead.
Emerging edge intelligence applications require the server to retrain and update deep neural networks deployed on remote edge nodes to leverage newly collected data samples. Unfortunately, it may be impossible in practice to continuously send fully updated weights to these edge nodes due to the highly constrained communication resource. In this paper, we propose the weight-wise deep partial updating paradigm, which smartly selects a small subset of weights to update in each server-to-edge communication round, while achieving a similar performance compared to full updating. Our method is established through analytically upper-bounding the loss difference between partial updating and full updating, and only updates the weights which make the largest contributions to the upper bound. Extensive experimental results demonstrate the efficacy of our partial updating methodology which achieves a high inference accuracy while updating a rather small number of weights.