# One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search

arXiv: https://arxiv.org/abs/2111.01203 · HTML: https://mlsanity.com/paper/2111.01203/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 51 references that are in the map.
- First posted on arXiv 1 Nov 2021.

## Builds on (most cited first, 30 of 36)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [Progressive Neural Architecture Search](https://mlsanity.com/paper/1712.00559/) (2017)
- [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.03443/) (2018)
- [NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search](https://mlsanity.com/paper/2001.00326/) (2020)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions](https://mlsanity.com/paper/2006.02903/) (2020)
- [Zero-Cost Proxies for Lightweight NAS](https://mlsanity.com/paper/2101.08134/) (2021)
- [BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models](https://mlsanity.com/paper/2003.11142/) (2020)
- [Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective](https://mlsanity.com/paper/2102.11535/) (2021)
- [NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications](https://mlsanity.com/paper/1804.03230/) (2018)
- [HAT: Hardware-Aware Transformers for Efficient Natural Language Processing](https://mlsanity.com/paper/2005.14187/) (2020)
- [BRP-NAS: Prediction-based NAS using GCNs](https://mlsanity.com/paper/2007.08668/) (2020)
- [APQ: Joint Search for Network Architecture, Pruning and Quantization Policy](https://mlsanity.com/paper/2006.08509/) (2020)
- [Single-Path NAS: Designing Hardware-Efficient ConvNets in less than 4 Hours](https://mlsanity.com/paper/1904.02877/) (2019)
- [HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmark](https://mlsanity.com/paper/2103.10584/) (2021)
- [AI Benchmark: All About Deep Learning on Smartphones in 2019](https://mlsanity.com/paper/1910.06663/) (2019)
- [ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptation](https://mlsanity.com/paper/1812.08934/) (2018)
- [Can weight sharing outperform random architecture search? An investigation with TuNAS](https://mlsanity.com/paper/2008.06120/) (2020)
- [Few-shot Neural Architecture Search](https://mlsanity.com/paper/2006.06863/) (2020)
- [NeuralPower: Predict and Deploy Energy-Efficient Convolutional Neural Networks](https://mlsanity.com/paper/1710.05420/) (2017)
- [CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment](https://mlsanity.com/paper/2104.12642/) (2021)
- [Standing on the Shoulders of Giants: Hardware and Neural Architecture Co-Search with Hot Start](https://mlsanity.com/paper/2007.09087/) (2020)
- [On Neural Architecture Search for Resource-Constrained Hardware Platforms](https://mlsanity.com/paper/1911.00105/) (2019)

## Built on by (most cited first, 8 of 8)

- [AccelTran: A Sparsity-Aware Accelerator for Dynamic Inference with Transformers](https://mlsanity.com/paper/2302.14705/) (2023)
- [AIO-P: Expanding Neural Performance Predictors Beyond Image Classification](https://mlsanity.com/paper/2211.17228/) (2022)
- [Neural Architecture Search for Energy Efficient Always-on Audio Models](https://mlsanity.com/paper/2202.05397/) (2022)
- [Efficient Deep Learning Infrastructures for Embedded Computing Systems: A Comprehensive Survey and Future Envision](https://mlsanity.com/paper/2411.01431/) (2024)
- [A Semi-Decoupled Approach to Fast and Optimal Hardware-Software Co-Design of Neural Accelerators](https://mlsanity.com/paper/2203.13921/) (2022)
- [Inference Latency Prediction at the Edge](https://mlsanity.com/paper/2210.02620/) (2022)
- [Hardware-Aware DNN Compression for Homogeneous Edge Devices](https://mlsanity.com/paper/2501.15240/) (2025)
- [Rank Portability Does Not Imply Feasibility Portability: Target-Specific Evaluation of Joint Hardware Constraints](https://mlsanity.com/paper/2609.22122/) (2026)

## Abstract (arXiv)

Convolutional neural networks (CNNs) are used in numerous real-world applications such as vision-based autonomous driving and video content analysis. To run CNN inference on various target devices, hardware-aware neural architecture search (NAS) is crucial. A key requirement of efficient hardware-aware NAS is the fast evaluation of inference latencies in order to rank different architectures. While building a latency predictor for each target device has been commonly used in state of the art, this is a very time-consuming process, lacking scalability in the presence of extremely diverse devices. In this work, we address the scalability challenge by exploiting latency monotonicity -- the architecture latency rankings on different devices are often correlated. When strong latency monotonicity exists, we can re-use architectures searched for one proxy device on new target devices, without losing optimality. In the absence of strong latency monotonicity, we propose an efficient proxy adaptation technique to significantly boost the latency monotonicity. Finally, we validate our approach and conduct experiments with devices of different platforms on multiple mainstream search spaces, including MobileNet-V2, MobileNet-V3, NAS-Bench-201, ProxylessNAS and FBNet. Our results highlight that, by using just one proxy device, we can find almost the same Pareto-optimal architectures as the existing per-device NAS, while avoiding the prohibitive cost of building a latency predictor for each device. GitHub: https://github.com/Ren-Research/OneProxy