FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision
This work addresses the problem of resource-intensive training for edge computing applications, offering an incremental improvement by combining quantization with an alternative training algorithm.
The paper tackles the inefficiency of backpropagation for training deep neural networks on edge devices by introducing FF-INT8, an INT8 quantized training approach based on the Forward-Forward algorithm, achieving 4.6% faster training, 8.3% energy savings, and 27.0% memory reduction on an NVIDIA Jetson Orin Nano board while maintaining competitive accuracy.
Backpropagation has been the cornerstone of neural network training for decades, yet its inefficiencies in time and energy consumption limit its suitability for resource-constrained edge devices. While low-precision neural network quantization has been extensively researched to speed up model inference, its application in training has been less explored. Recently, the Forward-Forward (FF) algorithm has emerged as a promising alternative to backpropagation, replacing the backward pass with an additional forward pass. By avoiding the need to store intermediate activations for backpropagation, FF can reduce memory footprint, making it well-suited for embedded devices. This paper presents an INT8 quantized training approach that leverages FF's layer-by-layer strategy to stabilize gradient quantization. Furthermore, we propose a novel "look-ahead" scheme to address limitations of FF and improve model accuracy. Experiments conducted on NVIDIA Jetson Orin Nano board demonstrate 4.6% faster training, 8.3% energy savings, and 27.0% reduction in memory usage, while maintaining competitive accuracy compared to the state-of-the-art.