mlsanityData to 7 Oct 2026

HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance Scaling

arXiv 2212.03354 ↗First posted 6 Dec 2022cs.LG cs.AR cs.NEcited by 14

Not on the map. Why?

Abstract (arXiv)

Dynamic neural networks (DyNNs) have become viable techniques to enable intelligence on resource-constrained edge devices while maintaining computational efficiency. In many cases, the implementation of DyNNs can be sub-optimal due to its underlying backbone architecture being developed at the design stage independent of both: (i) the dynamic computing features, e.g. early exiting, and (ii) the resource efficiency features of the underlying hardware, e.g., dynamic voltage and frequency scaling (DVFS). Addressing this, we present HADAS, a novel Hardware-Aware Dynamic Neural Architecture Search framework that realizes DyNN architectures whose backbone, early exiting features, and DVFS settings have been jointly optimized to maximize performance and resource efficiency. Our experiments using the CIFAR-100 dataset and a diverse set of edge computing platforms have seen HADAS dynamic models achieve up to 57% energy efficiency gains compared to the conventional dynamic ones while maintaining the desired level of accuracy scores. Our code is available at https://github.com/HalimaBouzidi/HADAS

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 11 of its 17 references that are in the map. First posted on arXiv 6 Dec 2022.

Builds on

11 of 17 references.

References · 11

  1. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  2. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 591
  3. 2021Dynamic Neural Networks: A Surveycited by 405
  4. 2020EdgeBERT: Sentence-Level Energy Optimizations for Latency-Aware Multi-Task NLP Inferencecited by 69
  5. 2015Conditional Deep Learning for Energy-Efficient and Enhanced Pattern Recognitioncited by 67
  6. 2020AttentiveNAS: Improving Neural Architecture Search via Attentive Samplingcited by 65
  7. 2020HAPI: Hardware-Aware Progressive Inferencecited by 30
  8. 2022Predictive Exit: Prediction of Fine-Grained Early Exits for Computation- and Energy-Efficient Inferencecited by 24
  9. 2021Dynamic-OFA: Runtime DNN Architecture Switching for Performance Scaling on Heterogeneous Embedded Platformscited by 18
  10. 2019S2DNAS:Transforming Static CNN Model for Dynamic Inference via Neural Architecture Searchcited by 14
  11. 2019A Novel Design of Adaptive and Hierarchical Convolutional Neural Networks using Partial Reconfiguration on FPGAcited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 5; 2025: 3; 2026: 3.

14 papers.

Sort:

By area:

  1. 2023Map-and-Conquer: Energy-Efficient Mapping of Dynamic Neural Nets onto Heterogeneous MPSoCscited by 9
  2. 2023MaGNAS: A Mapping-Aware Graph Neural Architecture Search Framework for Heterogeneous MPSoC Deploymentcited by 9
  3. 2024NACHOS: Neural Architecture Search for Hardware Constrained Early Exit Neural Networkscited by 9
  4. 2023Harmonic-NAS: Hardware-Aware Multimodal Neural Architecture Search on Resource-constrained Devicescited by 8
  5. 2025HH-PIM: Dynamic Optimization of Power and Performance with Heterogeneous-Hybrid PIM for Edge AI Devicescited by 2
  6. 2024SONATA: Self-adaptive Evolutionary Framework for Hardware-aware Neural Architecture Searchcited by 1
  7. 2024CARIn: Constraint-Aware and Responsive Inference on Heterogeneous Devices for Single- and Multi-DNN Workloadscited by 1
  8. 2025AEBNAS: Strengthening Exit Branches in Early-Exit Networks through Hardware-Aware Neural Architecture Searchcited by 1
  9. 2024Fluid Dynamic DNNs for Reliable and Adaptive Distributed Inference on Edge Devicescited by 0
  10. 2024Efficient Post-Training Augmentation for Adaptive Inference in Heterogeneous and Distributed IoT Environmentscited by 0
  11. 2025Hardware-Algorithm Co-Optimization of Early-Exit Neural Networks for Multi-Core Edge Acceleratorscited by 0
  12. 2026Efficient Deep Learning for Biometrics: Overview, Challenges and Trends in Ear of Frugal AIcited by 0
2 more
  1. 2026HERCULES: Hardware-Efficient, Robust, Continual Learning Neural Architecture Searchcited by 0
  2. 2026Deep Learning for Anomaly Detection in Railway Systems: A Structured Surveycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2021A Competitive Edge: Can FPGAs Beat GPUs at DCNN Inference Acceleration in Resource-Limited Edge Computing Applications?
  2. 2022Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs
  3. 2026A Comparative Study of CNN Optimization Methods for Edge AI: Exploring the Role of Early Exits
  4. 2026Enabling Spatially Fine-Grained DVFS in Neural Processing Units for Energy-Efficient LLM Serving
  5. 2023AdaMEC: Towards a Context-Adaptive and Dynamically-Combinable DNN Deployment Framework for Mobile Edge Computing
  6. 2026EdgeServing: Deadline-Aware Multi-DNN Serving at the Edge
  7. 2025Enabling Efficient Processing of Spiking Neural Networks with On-Chip Learning on Commodity Neuromorphic Processors for Edge AI Systems
  8. 2025E4: Energy-Efficient DNN Inference for Edge Video Analytics Via Early-Exit and DVFS