NITRO-D: Native Integer-only Training of Deep Convolutional Neural Networks

• URL: http://arxiv.org/abs/2407.11698v2
• Date: Thu, 12 Sep 2024 14:18:22 GMT
• Title: NITRO-D: Native Integer-only Training of Deep Convolutional Neural Networks
• Authors: Alberto Pirillo, Luca Colombo, Manuel Roveri,
• Abstract summary: This work introduces NITRO-D, a new framework for training arbitrarily deep integer-only Convolutional Neural Networks (CNNs) NiTRO-D is the first framework in the literature enabling the training of integer-only CNNs without the need to introduce a quantization scheme.
• Score: 2.6230959823681834
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantization has become increasingly pivotal in addressing the steadily increasing computational and memory requirements of Deep Neural Networks (DNNs). By reducing the number of bits used to represent weights and activations (typically from 32-bit floating-point to 16-bit or 8-bit integers), quantization reduces the memory footprint, energy consumption, and execution time of DNN models. However, traditional quantization methods typically focus on the inference of DNNs, while the training process still relies on floating-point operations. To date, only one work in the literature has addressed integer-only training for Multi-Layer Perceptron (MLP) architectures. This work introduces NITRO-D, a new framework for training arbitrarily deep integer-only Convolutional Neural Networks (CNNs) that operate entirely in the integer-only domain for both training and inference. NITRO-D is the first framework in the literature enabling the training of integer-only CNNs without the need to introduce a quantization scheme. Specifically, NITRO-D introduces a novel architecture integrating multiple integer local-loss blocks, which include the proposed NITRO Scaling Layer and the NITRO-ReLU activation function. Additionally, it introduces a novel integer-only learning algorithm derived from Local Error Signals (LES), utilizing IntegerSGD, an optimizer specifically designed to operate in an integer-only context. NITRO-D is implemented in an open-source Python library. Extensive experimental evaluations demonstrate its effectiveness across several state-of-the-art image recognition datasets. Results show significant performance improvements from 2.47% to 5.96% for integer-only MLP architectures over the state-of-the-art solution, and the capability of training integer-only CNN architectures with minimal accuracy degradation from -0.15% to -4.22% compared to floating-point LES.

Related papers

• PocketNN: Integer-only Training and Inference of Neural Networks via Direct Feedback Alignment and Pocket Activations in Pure C++ [10.508187462682308]
  Deep learning algorithms are implemented using floating-point real numbers. This presents an obstacle for implementing them on low-end devices which may not have dedicated floating-point units (FPUs)
  arXiv  Detail & Related papers  (2022-01-08T16:52:34Z)
• Efficient and Robust Mixed-Integer Optimization Methods for Training Binarized Deep Neural Networks [0.07614628596146598]
  We study deep neural networks with binary activation functions and continuous or integer weights (BDNN) We show that the BDNN can be reformulated as a mixed-integer linear program with bounded weight space which can be solved to global optimality by classical mixed-integer programming solvers. For the first time a robust model is presented which enforces robustness of the BDNN during training.
  arXiv  Detail & Related papers  (2021-10-21T18:02:58Z)
• Sub-bit Neural Networks: Learning to Compress and Accelerate Binary Neural Networks [72.81092567651395]
  Sub-bit Neural Networks (SNNs) are a new type of binary quantization design tailored to compress and accelerate BNNs. SNNs are trained with a kernel-aware optimization framework, which exploits binary quantization in the fine-grained convolutional kernel space. Experiments on visual recognition benchmarks and the hardware deployment on FPGA validate the great potentials of SNNs.
  arXiv  Detail & Related papers  (2021-10-18T11:30:29Z)
• iRNN: Integer-only Recurrent Neural Network [0.8766022970635899]
  We present a quantization-aware training method for obtaining a highly accurate integer-only recurrent neural network (iRNN) Our iRNN maintains similar performance as its full-precision counterpart, their deployment on smartphones improves the runtime performance by $2times$, and reduces the model size by $4times$.
  arXiv  Detail & Related papers  (2021-09-20T20:17:40Z)
• Quantized Neural Networks via {-1, +1} Encoding Decomposition and Acceleration [83.84684675841167]
  We propose a novel encoding scheme using -1, +1 to decompose quantized neural networks (QNNs) into multi-branch binary networks. We validate the effectiveness of our method on large-scale image classification, object detection, and semantic segmentation tasks.
  arXiv  Detail & Related papers  (2021-06-18T03:11:15Z)
• 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)
• GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training [59.160154997555956]
  We present GradInit, an automated and architecture method for initializing neural networks. It is based on a simple agnostic; the variance of each network layer is adjusted so that a single step of SGD or Adam results in the smallest possible loss value. It also enables training the original Post-LN Transformer for machine translation without learning rate warmup.
  arXiv  Detail & Related papers  (2021-02-16T11:45:35Z)
• NITI: Training Integer Neural Networks Using Integer-only Arithmetic [4.361357921751159]
  We present NITI, an efficient deep neural network training framework that computes exclusively with integer arithmetic. A proof-of-concept open-source software implementation of NITI that utilizes native 8-bit integer operations is presented. NITI achieves negligible accuracy degradation on the MNIST and CIFAR10 datasets using 8-bit integer storage and computation.
  arXiv  Detail & Related papers  (2020-09-28T07:41:36Z)
• AQD: Towards Accurate Fully-Quantized Object Detection [94.06347866374927]
  We propose an Accurate Quantized object Detection solution, termed AQD, to get rid of floating-point computation. Our AQD achieves comparable or even better performance compared with the full-precision counterpart under extremely low-bit schemes.
  arXiv  Detail & Related papers  (2020-07-14T09:07:29Z)
• Efficient Integer-Arithmetic-Only Convolutional Neural Networks [87.01739569518513]
  We replace conventional ReLU with Bounded ReLU and find that the decline is due to activation quantization. Our integer networks achieve equivalent performance as the corresponding FPN networks, but have only 1/4 memory cost and run 2x faster on modern GPU.
  arXiv  Detail & Related papers  (2020-06-21T08:23:03Z)

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.