FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision

• URL: http://arxiv.org/abs/2506.22771v1
• Date: Sat, 28 Jun 2025 06:16:26 GMT
• Title: FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision
• Authors: Jingxiao Ma, Priyadarshini Panda, Sherief Reda,
• Abstract summary: This paper presents an INT8 quantized training approach that leverages FF's layer-by-layer strategy to stabilize gradient quantization.<n> Experiments conducted on NVIDIA Jetson Orin Nano board demonstrate 4.6% faster training, 8.3% energy savings, and 27.0% reduction in memory usage.
• Score: 7.461536872552009
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• Towards Fully FP8 GEMM LLM Training at Scale [77.39425361120466]
  Existing approaches often rely on suboptimal fine-grained FP8 kernels or fall back to higher-precision matrix multiplications.<n>We introduce a new class of LLM architectures that, for the first time, support FP8 computation for all GEMMs within transformer blocks during both forward and backward passes.<n>This enables unprecedented throughput gains, particularly at scale, while matching the downstream performance of standard BF16 training.
  arXiv  Detail & Related papers  (2025-05-26T21:04:14Z)
• DNN Memory Footprint Reduction via Post-Training Intra-Layer Multi-Precision Quantization [0.0]
  This paper introduces a technique that effectively reduces the memory footprint of Deep Neural Network (DNN) models on resource-constrained edge devices. Our proposed technique, named Post-Training Intra-Layer Multi-Precision Quantization (PTILMPQ), employs a post-training quantization approach, eliminating the need for extensive training data.
  arXiv  Detail & Related papers  (2024-04-03T15:06:09Z)
• Quantized Neural Networks for Low-Precision Accumulation with Guaranteed Overflow Avoidance [68.8204255655161]
  We introduce a quantization-aware training algorithm that guarantees avoiding numerical overflow when reducing the precision of accumulators during inference. We evaluate our algorithm across multiple quantized models that we train for different tasks, showing that our approach can reduce the precision of accumulators while maintaining model accuracy with respect to a floating-point baseline.
  arXiv  Detail & Related papers  (2023-01-31T02:46:57Z)
• Efficient On-device Training via Gradient Filtering [14.484604762427717]
  We propose a new gradient filtering approach which enables on-device CNN model training. Our approach creates a special structure with fewer unique elements in the gradient map. Our approach opens up a new direction of research with a huge potential for on-device training.
  arXiv  Detail & Related papers  (2023-01-01T02:33:03Z)
• DIVISION: Memory Efficient Training via Dual Activation Precision [60.153754740511864]
  State-of-the-art work combines a search of quantization bit-width with the training, which makes the procedure complicated and less transparent. We propose a simple and effective method to compress DNN training. Experiment results show DIVISION has better comprehensive performance than state-of-the-art methods, including over 10x compression of activation maps and competitive training throughput, without loss of model accuracy.
  arXiv  Detail & Related papers  (2022-08-05T03:15:28Z)
• ActNN: Reducing Training Memory Footprint via 2-Bit Activation Compressed Training [68.63354877166756]
  ActNN is a memory-efficient training framework that stores randomly quantized activations for back propagation. ActNN reduces the memory footprint of the activation by 12x, and it enables training with a 6.6x to 14x larger batch size.
  arXiv  Detail & Related papers  (2021-04-29T05:50:54Z)
• FracTrain: Fractionally Squeezing Bit Savings Both Temporally and Spatially for Efficient DNN Training [62.932299614630985]
  We propose FracTrain that integrates progressive fractional quantization which gradually increases the precision of activations, weights, and gradients.<n>FracTrain reduces computational cost and hardware-quantified energy/latency of DNN training while achieving a comparable or better (-0.12%+1.87%) accuracy.
  arXiv  Detail & Related papers  (2020-12-24T05:24:10Z)
• Shifted and Squeezed 8-bit Floating Point format for Low-Precision Training of Deep Neural Networks [13.929168096016957]
  We introduce a novel methodology for training deep neural networks using 8-bit floating point (FP8) numbers. Reduced bit precision allows for a larger effective memory and increased computational speed. We show that, unlike previous 8-bit precision training methods, the proposed method works out-of-the-box for representative models.
  arXiv  Detail & Related papers  (2020-01-16T06:38:27Z)
• Towards Unified INT8 Training for Convolutional Neural Network [83.15673050981624]
  We build a unified 8-bit (INT8) training framework for common convolutional neural networks. First, we empirically find the four distinctive characteristics of gradients, which provide us insightful clues for gradient quantization. We propose two universal techniques, including Direction Sensitive Gradient Clipping that reduces the direction deviation of gradients.
  arXiv  Detail & Related papers  (2019-12-29T08:37:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.