ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks

• URL: http://arxiv.org/abs/2205.08119v1
• Date: Tue, 17 May 2022 06:40:13 GMT
• Title: ShiftAddNAS: Hardware-Inspired Search for More Accurate and Efficient Neural Networks
• Authors: Haoran You, Baopu Li, Huihong Shi, Yonggan Fu, Yingyan Lin
• Abstract summary: ShiftAddNAS can automatically search for more accurate and more efficient NNs. ShiftAddNAS integrates the first hybrid search space that incorporates both multiplication-based and multiplication-free operators. Experiments and ablation studies consistently validate the efficacy of ShiftAddNAS.
• Score: 42.28659737268829
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Neural networks (NNs) with intensive multiplications (e.g., convolutions and transformers) are capable yet power hungry, impeding their more extensive deployment into resource-constrained devices. As such, multiplication-free networks, which follow a common practice in energy-efficient hardware implementation to parameterize NNs with more efficient operators (e.g., bitwise shifts and additions), have gained growing attention. However, multiplication-free networks usually under-perform their vanilla counterparts in terms of the achieved accuracy. To this end, this work advocates hybrid NNs that consist of both powerful yet costly multiplications and efficient yet less powerful operators for marrying the best of both worlds, and proposes ShiftAddNAS, which can automatically search for more accurate and more efficient NNs. Our ShiftAddNAS highlights two enablers. Specifically, it integrates (1) the first hybrid search space that incorporates both multiplication-based and multiplication-free operators for facilitating the development of both accurate and efficient hybrid NNs; and (2) a novel weight sharing strategy that enables effective weight sharing among different operators that follow heterogeneous distributions (e.g., Gaussian for convolutions vs. Laplacian for add operators) and simultaneously leads to a largely reduced supernet size and much better searched networks. Extensive experiments and ablation studies on various models, datasets, and tasks consistently validate the efficacy of ShiftAddNAS, e.g., achieving up to a +7.7% higher accuracy or a +4.9 better BLEU score compared to state-of-the-art NN, while leading to up to 93% or 69% energy and latency savings, respectively. Codes and pretrained models are available at https://github.com/RICE-EIC/ShiftAddNAS.

Related papers

• ShiftAddAug: Augment Multiplication-Free Tiny Neural Network with Hybrid Computation [7.143509813507735]
  ShiftAddAug uses costly multiplication to augment efficient but less powerful multiplication-free operators, improving performance without any inference overhead. It secures up to a 4.95% increase in accuracy on the CIFAR100 compared to its directly trained counterparts, even surpassing the performance of multiplicative NNs.
  arXiv  Detail & Related papers  (2024-07-03T07:56:51Z)
• DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization [27.231327287238102]
  We propose the DenseShift network, which significantly improves the accuracy of Shift networks. Our experiments on various computer vision and speech tasks demonstrate that DenseShift outperforms existing low-bit multiplication-free networks.
  arXiv  Detail & Related papers  (2022-08-20T15:17:40Z)
• Two Sparsities Are Better Than One: Unlocking the Performance Benefits of Sparse-Sparse Networks [0.0]
  We introduce Complementary Sparsity, a technique that significantly improves the performance of dual sparse networks on existing hardware. We show up to 100X improvement in throughput and energy efficiency performing inference on FPGAs. Our results suggest that weight plus activation sparsity can be a potent combination for efficiently scaling future AI models.
  arXiv  Detail & Related papers  (2021-12-27T20:41:01Z)
• Adder Neural Networks [75.54239599016535]
  We present adder networks (AdderNets) to trade massive multiplications in deep neural networks. In AdderNets, we take the $ell_p$-norm distance between filters and input feature as the output response. We show that the proposed AdderNets can achieve 75.7% Top-1 accuracy 92.3% Top-5 accuracy using ResNet-50 on the ImageNet dataset.
  arXiv  Detail & Related papers  (2021-05-29T04:02:51Z)
• AdderNet and its Minimalist Hardware Design for Energy-Efficient Artificial Intelligence [111.09105910265154]
  We present a novel minimalist hardware architecture using adder convolutional neural network (AdderNet) The whole AdderNet can practically achieve 16% enhancement in speed. We conclude the AdderNet is able to surpass all the other competitors.
  arXiv  Detail & Related papers  (2021-01-25T11:31:52Z)
• ShiftAddNet: A Hardware-Inspired Deep Network [87.18216601210763]
  ShiftAddNet is an energy-efficient multiplication-less deep neural network. It leads to both energy-efficient inference and training, without compromising expressive capacity. ShiftAddNet aggressively reduces over 80% hardware-quantified energy cost of DNNs training and inference, while offering comparable or better accuracies.
  arXiv  Detail & Related papers  (2020-10-24T05:09:14Z)
• ReActNet: Towards Precise Binary Neural Network with Generalized Activation Functions [76.05981545084738]
  We propose several ideas for enhancing a binary network to close its accuracy gap from real-valued networks without incurring any additional computational cost. We first construct a baseline network by modifying and binarizing a compact real-valued network with parameter-free shortcuts. We show that the proposed ReActNet outperforms all the state-of-the-arts by a large margin.
  arXiv  Detail & Related papers  (2020-03-07T02:12:02Z)
• AdderNet: Do We Really Need Multiplications in Deep Learning? [159.174891462064]
  We present adder networks (AdderNets) to trade massive multiplications in deep neural networks for much cheaper additions to reduce computation costs. We develop a special back-propagation approach for AdderNets by investigating the full-precision gradient. As a result, the proposed AdderNets can achieve 74.9% Top-1 accuracy 91.7% Top-5 accuracy using ResNet-50 on the ImageNet dataset.
  arXiv  Detail & Related papers  (2019-12-31T06:56:47Z)

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.