# HELP: Hardware-Adaptive Efficient Latency Prediction for NAS via Meta-Learning

arXiv: https://arxiv.org/abs/2106.08630 · HTML: https://mlsanity.com/paper/2106.08630/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 64 references that are in the map.
- First posted on arXiv 16 Jun 2021.

## Builds on (most cited first, 30 of 44)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks](https://mlsanity.com/paper/1703.03400/) (2017)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Prototypical Networks for Few-shot Learning](https://mlsanity.com/paper/1703.05175/) (2017)
- [Matching Networks for One Shot Learning](https://mlsanity.com/paper/1606.04080/) (2016)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [On First-Order Meta-Learning Algorithms](https://mlsanity.com/paper/1803.02999/) (2018)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [Efficient Neural Architecture Search via Parameter Sharing](https://mlsanity.com/paper/1802.03268/) (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)
- [Meta-Learning with Differentiable Convex Optimization](https://mlsanity.com/paper/1904.03758/) (2019)
- [NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search](https://mlsanity.com/paper/2001.00326/) (2020)
- [Meta-SGD: Learning to Learn Quickly for Few-Shot Learning](https://mlsanity.com/paper/1707.09835/) (2017)
- [NAS-Bench-101: Towards Reproducible Neural Architecture Search](https://mlsanity.com/paper/1902.09635/) (2019)
- [Attentive Neural Processes](https://mlsanity.com/paper/1901.05761/) (2019)
- [Designing Neural Network Architectures using Reinforcement Learning](https://mlsanity.com/paper/1611.02167/) (2016)
- [PC-DARTS: Partial Channel Connections for Memory-Efficient Architecture Search](https://mlsanity.com/paper/1907.05737/) (2019)
- [Searching for A Robust Neural Architecture in Four GPU Hours](https://mlsanity.com/paper/1910.04465/) (2019)
- [cuDNN: Efficient Primitives for Deep Learning](https://mlsanity.com/paper/1410.0759/) (2014)
- [Pay Less Attention with Lightweight and Dynamic Convolutions](https://mlsanity.com/paper/1901.10430/) (2019)
- [BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models](https://mlsanity.com/paper/2003.11142/) (2020)
- [Neural Architecture Optimization](https://mlsanity.com/paper/1808.07233/) (2018)

## Built on by (most cited first, 16 of 16)

- [System-status-aware Adaptive Network for Online Streaming Video Understanding](https://mlsanity.com/paper/2303.15742/) (2023)
- [Encodings for Prediction-based Neural Architecture Search](https://mlsanity.com/paper/2403.02484/) (2024)
- [One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2111.01203/) (2021)
- [On Latency Predictors for Neural Architecture Search](https://mlsanity.com/paper/2403.02446/) (2024)
- [A Hardware-Aware Framework for Accelerating Neural Architecture Search Across Modalities](https://mlsanity.com/paper/2205.10358/) (2022)
- [Multi-Predict: Few Shot Predictors For Efficient Neural Architecture Search](https://mlsanity.com/paper/2306.02459/) (2023)
- [MAPLE: Microprocessor A Priori for Latency Estimation](https://mlsanity.com/paper/2111.15106/) (2021)
- [FedorAS: Federated Architecture Search under system heterogeneity](https://mlsanity.com/paper/2206.11239/) (2022)
- [DASS: Differentiable Architecture Search for Sparse neural networks](https://mlsanity.com/paper/2207.06968/) (2022)
- [How Much Is Hidden in the NAS Benchmarks? Few-Shot Adaptation of a NAS Predictor](https://mlsanity.com/paper/2311.18451/) (2023)
- [Where to Begin: Efficient Pretraining via Subnetwork Selection and Distillation](https://mlsanity.com/paper/2510.07227/) (2025)
- [MAPLE-X: Latency Prediction with Explicit Microprocessor Prior Knowledge](https://mlsanity.com/paper/2205.12660/) (2022)
- [SCAN-Edge: Finding MobileNet-speed Hybrid Networks for Diverse Edge Devices via Hardware-Aware Evolutionary Search](https://mlsanity.com/paper/2408.15395/) (2024)
- [HiFi-LLP: High-Fidelity, Low-Cost Latency Predictors with Confidence for Robust HW-NAS](https://mlsanity.com/paper/2607.11746/) (2026)
- [Transferable Latency Prediction for Fast LLM Screening on Heterogeneous Edge Devices](https://mlsanity.com/paper/2607.21602/) (2026)
- [Rank Portability Does Not Imply Feasibility Portability: Target-Specific Evaluation of Joint Hardware Constraints](https://mlsanity.com/paper/2609.22122/) (2026)

## Abstract (arXiv)

For deployment, neural architecture search should be hardware-aware, in order to satisfy the device-specific constraints (e.g., memory usage, latency and energy consumption) and enhance the model efficiency. Existing methods on hardware-aware NAS collect a large number of samples (e.g., accuracy and latency) from a target device, either builds a lookup table or a latency estimator. However, such approach is impractical in real-world scenarios as there exist numerous devices with different hardware specifications, and collecting samples from such a large number of devices will require prohibitive computational and monetary cost. To overcome such limitations, we propose Hardware-adaptive Efficient Latency Predictor (HELP), which formulates the device-specific latency estimation problem as a meta-learning problem, such that we can estimate the latency of a model's performance for a given task on an unseen device with a few samples. To this end, we introduce novel hardware embeddings to embed any devices considering them as black-box functions that output latencies, and meta-learn the hardware-adaptive latency predictor in a device-dependent manner, using the hardware embeddings. We validate the proposed HELP for its latency estimation performance on unseen platforms, on which it achieves high estimation performance with as few as 10 measurement samples, outperforming all relevant baselines. We also validate end-to-end NAS frameworks using HELP against ones without it, and show that it largely reduces the total time cost of the base NAS method, in latency-constrained settings. Code is available at https://github.com/HayeonLee/HELP.