Pith. sign in

REVIEW 10 cited by

A Comprehensive Survey on Hardware-Aware Neural Architecture Search

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2101.09336 v1 pith:THZIFK53 submitted 2021-01-22 cs.LG cs.CC

Hadjer Benmeziane , Kaoutar El Maghraoui , Hamza Ouarnoughi , Smail Niar , Martin Wistuba , Naigang Wang This is my paper · ORCID
classification cs.LGcs.CC
keywords beensearchhardware-awarearchitectureneuralsignificantsurveyalgorithms
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Neural Architecture Search (NAS) methods have been growing in popularity. These techniques have been fundamental to automate and speed up the time consuming and error-prone process of synthesizing novel Deep Learning (DL) architectures. NAS has been extensively studied in the past few years. Arguably their most significant impact has been in image classification and object detection tasks where the state of the art results have been obtained. Despite the significant success achieved to date, applying NAS to real-world problems still poses significant challenges and is not widely practical. In general, the synthesized Convolution Neural Network (CNN) architectures are too complex to be deployed in resource-limited platforms, such as IoT, mobile, and embedded systems. One solution growing in popularity is to use multi-objective optimization algorithms in the NAS search strategy by taking into account execution latency, energy consumption, memory footprint, etc. This kind of NAS, called hardware-aware NAS (HW-NAS), makes searching the most efficient architecture more complicated and opens several questions. In this survey, we provide a detailed review of existing HW-NAS research and categorize them according to four key dimensions: the search space, the search strategy, the acceleration technique, and the hardware cost estimation strategies. We further discuss the challenges and limitations of existing approaches and potential future directions. This is the first survey paper focusing on hardware-aware NAS. We hope it serves as a valuable reference for the various techniques and algorithms discussed and paves the road for future research towards hardware-aware NAS.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. MoENAS: Mixture-of-Expert based Neural Architecture Search for jointly Accurate, Fair, and Robust Edge Deep Neural Networks

    cs.LG 2025-02 reject novelty 6.0 of 10

    MoENAS, a mixture-of-experts neural architecture search, produces MobileViTv2 variants with reported accuracy, fairness, robustness, and generalization gains over state-of-the-art edge DNNs on person classification.

  2. Filling the Pareto-Optimal Front for Affordance Segmentation on Embedded Devices Using RGB-D Cameras

    cs.CV 2026-07 conditional novelty 5.0 of 10

    HW-NAS with an RGB-D search space and a cheap depth-to-RGB fine-tune layer yield mid-size networks that often sit on the accuracy–FLOPs/params Pareto front and run real-time on a Jetson Nano.

  3. Examining the Efficacy of Graph Neural Network Message-Passing in Regression Contexts

    cs.LG 2026-07 conditional novelty 5.0 of 10

    Across four NAS/DNN-predictor regression benchmarks, GEN (deep graph convolution) achieves the best average rank over 11 GNN message-passing layers, though attention GATv2 wins on the largest graphs.

  4. BearingNAS: Obtaining In-Sensor Intelligent Fault Diagnosis Systems for Bearings Using a Laptop

    cs.LG 2026-06 conditional novelty 5.0 of 10

    BearingNAS automatically designs a 99.5%-accurate bearing fault classifier that fits in 7 kiB RAM and runs on the LSM6DSO16IS in-sensor processor, with the search completing on a laptop in under an hour.

  5. Automated Charge Transition Detection in Quantum Dot Charge Stability Diagrams

    cond-mat.mes-hall 2025-08 unverdicted novelty 5.0 of 10

    Automated charge transition detection in quantum dot stability diagrams, trained on simulated data and validated on experimental GaAs and SiGe qubit samples.

  6. Data Aware Differentiable Neural Architecture Search for Tiny Keyword Spotting Applications

    cs.LG 2025-07 conditional novelty 5.0 of 10

    Data Aware Differentiable NAS co-optimizes model architecture and MFCC data configuration via continuous relaxation, achieving 97.6% accuracy with 298K parameters on Google Speech Commands.

  7. Lightweight Neural Networks for Affordance Segmentation: Enhancement of the Decoder Module

    cs.CV 2026-07 conditional novelty 4.0 of 10

    Small decoder design choices (depthwise vs. standard convolutions, upsampling type, and an auxiliary object-segmentation head) yield modest accuracy gains over the authors' prior baseline on binary grasp affordance se...

  8. Toward Edge General Intelligence with Agentic AI and Agentification: Concepts, Technologies, and Future Directions

    cs.NI 2025-08 conditional novelty 4.0 of 10

    A survey that organizes agentic AI for 6G edge networks into four pillars, compactness, efficiency, knowledge and reasoning, and migration, and illustrates them with prior case studies.

  9. Energy-Efficient Deep Learning for Traffic Classification on Microcontrollers

    cs.NI 2025-06 conditional novelty 4.0 of 10

    A hardware-aware searched 1D-CNN classifies encrypted traffic on STM32 microcontrollers with 96.59% accuracy, 10.08M FLOPs, and 7.86-29.10 mJ per inference.

  10. Searching Neural Architectures for Sensor Nodes on IoT Gateways

    cs.LG 2025-05 conditional novelty 4.0 of 10

    GatewayNAS adapts the hardware-aware neural architecture search space to the time and energy budget of an IoT gateway, producing tiny CNNs for sensor nodes without cloud data transfer.

Pith tools