Year: 2025
Type: preprint
Abstract: Training on edge devices enables personalized model fine-tuning to enhance real-world performance and maintain data privacy. However, the gradient computation for backpropagation in the training requires significant memory buffers to store intermediate features and compute losses. This is unacceptable for memory-constrained edge devices such as microcontrollers. To tackle this issue, we propose a training acceleration method using dynamic gradient sparse updates. This method updates the important channels and layers only and skips gradient computation for the less important channels and layers to reduce memory usage for each update iteration. In addition, the channel selection is dynamic for different iterations to traverse most of the parameters in the update layers along the time dimension for better performance. The experimental result shows that the proposed method enables an ImageNet pre-trained MobileNetV2 trained on CIFAR-10 to achieve an accuracy of 85.77\% while updating only 2\% of convolution weights within 256KB on-chip memory. This results in a remarkable 98\% reduction in feature memory usage compared to dense model training.
Source: arXiv (Cornell University)
Authors: Li, I-Hsuan, Chang, Tian-Sheuan
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W6979259089
Cites:
Cited by:
Related to: