mlsanityData to 14 Oct 2026

Energy-Aware Deep Learning on Resource-Constrained Hardware

arXiv 2505.12523 ↗First posted 18 May 2025cs.LG cs.ARcited by 3

Not on the map. Why?

Abstract (arXiv)

The use of deep learning (DL) on Internet of Things (IoT) and mobile devices offers numerous advantages over cloud-based processing. However, such devices face substantial energy constraints to prolong battery-life, or may even operate intermittently via energy-harvesting. Consequently, textitenergy-aware approaches for optimizing DL inference and training on such resource-constrained devices have garnered recent interest. We present an overview of such approaches, outlining their methodologies, implications for energy consumption and system-level efficiency, and their limitations in terms of supported network types, hardware platforms, and application scenarios. We hope our review offers a clear synthesis of the evolving energy-aware DL landscape and serves as a foundation for future research in energy-constrained computing.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 94 of its 169 references that are in the map. First posted on arXiv 18 May 2025.

Builds on

94 of 169 references.

References · 94

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  3. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  4. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  5. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  6. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  7. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
  8. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  9. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  10. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
  11. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  12. 2016XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networkscited by 849
38 more
  1. 2016Training Deep Nets with Sublinear Memory Costcited by 848
  2. 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 763
  3. 2022Fine-Tuning can Distort Pretrained Features and Underperform Out-of-Distributioncited by 739
  4. 2017Dynamic Routing Between Capsulescited by 689
  5. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  6. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 596
  7. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 521
  8. 2019Robust and Communication-Efficient Federated Learning from Non-IID Datacited by 419
  9. 2020NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Searchcited by 416
  10. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 409
  11. 2017SkipNet: Learning Dynamic Routing in Convolutional Networkscited by 332
  12. 2020DeeBERT: Dynamic Early Exiting for Accelerating BERT Inferencecited by 332
  13. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 316
  14. 2018Slimmable Neural Networkscited by 305
  15. 2020MCUNet: Tiny Deep Learning on IoT Devicescited by 273
  16. 2020A Comprehensive Survey of Neural Architecture Search: Challenges and Solutionscited by 254
  17. 2021AdaViT: Adaptive Vision Transformers for Efficient Image Recognitioncited by 228
  18. 2020Domain Generalization using Causal Matchingcited by 225
  19. 2018To Trust Or Not To Trust A Classifiercited by 207
  20. 2022Surgical Fine-Tuning Improves Adaptation to Distribution Shiftscited by 205
  21. 2018Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)cited by 191
  22. 2017BlockDrop: Dynamic Inference Paths in Residual Networkscited by 189
  23. 2019Energy Efficient Federated Learning Over Wireless Communication Networkscited by 181
  24. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  25. 2018SpotTune: Transfer Learning through Adaptive Fine-tuningcited by 168
  26. 2020Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semanticscited by 161
  27. 2022On-Device Training Under 256KB Memorycited by 160
  28. 2020A Survey on Evolutionary Neural Architecture Searchcited by 142
  29. 2016Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruningcited by 134
  30. 2018Dynamic Channel Pruning: Feature Boosting and Suppressioncited by 129
  31. 2016Spatially Adaptive Computation Time for Residual Networkscited by 118
  32. 2020Learning to Learn with Variational Information Bottleneck for Domain Generalizationcited by 102
  33. 2019Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregationcited by 100
  34. 2019What Would Elsa Do? Freezing Layers During Transformer Fine-Tuningcited by 89
  35. 2021HW-NAS-Bench:Hardware-Aware Neural Architecture Search Benchmarkcited by 84
  36. 2020Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approachcited by 81
  37. 2018JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Servicescited by 80
  38. 2018ChamNet: Towards Efficient Network Design through Platform-Aware Model Adaptationcited by 76

50 most cited of 94 All 94 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Quantum Reservoir Computing for Short-Term Power Load Forecasting in Resource-Constrained Energy Systemscited by 1
  2. 2026Efficient Deep Learning for Biometrics: Overview, Challenges and Trends in Ear of Frugal AIcited by 0
  3. 2026Towards automatic smoke detector inspection: Recognition of the smoke detectors in industrial facilities and preparation for future drone integrationcited by 0