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

by   Haoran You, et al.

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 NN, while leading to up to 93 Codes and pretrained models are available at


page 1

page 2

page 3

page 4


NASA: Neural Architecture Search and Acceleration for Hardware Inspired Hybrid Networks

Multiplication is arguably the most cost-dominant operation in modern de...

ShiftAddNet: A Hardware-Inspired Deep Network

Multiplication (e.g., convolution) is arguably a cornerstone of modern d...

GhostShiftAddNet: More Features from Energy-Efficient Operations

Deep convolutional neural networks (CNNs) are computationally and memory...

SPIN: An Empirical Evaluation on Sharing Parameters of Isotropic Networks

Recent isotropic networks, such as ConvMixer and vision transformers, ha...

ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer

Vision Transformers (ViTs) have shown impressive performance and have be...

Locally Free Weight Sharing for Network Width Search

Searching for network width is an effective way to slim deep neural netw...

Restructurable Activation Networks

Is it possible to restructure the non-linear activation functions in a d...

Please sign up or login with your details

Forgot password? Click here to reset