mlsanityData to 14 Oct 2026

Enabling Resource-efficient AIoT System with Cross-level Optimization: A survey

arXiv 2309.15467 ↗First posted 27 Sep 2023cs.LG cs.AI cs.DCcited by 8

Not on the map. Why?

Abstract (arXiv)

The emerging field of artificial intelligence of things (AIoT, AI+IoT) is driven by the widespread use of intelligent infrastructures and the impressive success of deep learning (DL). With the deployment of DL on various intelligent infrastructures featuring rich sensors and weak DL computing capabilities, a diverse range of AIoT applications has become possible. However, DL models are notoriously resource-intensive. Existing research strives to realize near-/realtime inference of AIoT live data and low-cost training using AIoT datasets on resource-scare infrastructures. Accordingly, the accuracy and responsiveness of DL models are bounded by resource availability. To this end, the algorithm-system co-design that jointly optimizes the resource-friendly DL models and model-adaptive system scheduling improves the runtime resource availability and thus pushes the performance boundary set by the standalone level. Unlike previous surveys on resource-friendly DL models or hand-crafted DL compilers/frameworks with partially fine-tuned components, this survey aims to provide a broader optimization space for more free resource-performance tradeoffs. The cross-level optimization landscape involves various granularity, including the DL model, computation graph, operator, memory schedule, and hardware instructor in both on-device and distributed paradigms. Furthermore, due to the dynamic nature of AIoT context, which includes heterogeneous hardware, agnostic sensing data, varying user-specified performance demands, and resource constraints, this survey explores the context-aware inter-/intra-device controllers for automatic cross-level adaptation. Additionally, we identify some potential directions for resource-efficient AIoT systems. By consolidating problems and techniques scattered over diverse levels, we aim to help readers understand their connections and stimulate further discussions.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 157 of its 366 references that are in the map. First posted on arXiv 27 Sep 2023.

Builds on

157 of 366 references.

References · 157

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2014Going Deeper with Convolutionscited by 4,241
  7. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  8. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  9. 2016Wide Residual Networkscited by 3,070
  10. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  11. 2021SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformerscited by 2,940
  12. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,329
38 more
  1. 2021Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processingcited by 2,234
  2. 2019Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelismcited by 1,868
  3. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,512
  4. 2017Mixed Precision Trainingcited by 1,156
  5. 2017Learning Transferable Architectures for Scalable Image Recognitioncited by 1,101
  6. 2016SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizecited by 1,060
  7. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  8. 2016Training Deep Nets with Sublinear Memory Costcited by 848
  9. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 823
  10. 2017Channel Pruning for Accelerating Very Deep Neural Networkscited by 702
  11. 2013Network In Networkcited by 605
  12. 2015BinaryConnect: Training Deep Neural Networks with binary weights during propagationscited by 592
  13. 2019Segmentation Transformer: Object-Contextual Representations for Semantic Segmentationcited by 576
  14. 2016DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradientscited by 569
  15. 2020Zero-Reference Deep Curve Estimation for Low-Light Image Enhancementcited by 542
  16. 2022Continual Test-Time Domain Adaptationcited by 525
  17. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 518
  18. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 494
  19. 2017ThiNet: A Filter Level Pruning Method for Deep Neural Network Compressioncited by 442
  20. 2019Federated Learning in Mobile Edge Networks: A Comprehensive Surveycited by 408
  21. 2015Deep Learning with Limited Numerical Precisioncited by 376
  22. 2019Deep Learning Recommendation Model for Personalization and Recommendation Systemscited by 327
  23. 2017A Survey of Model Compression and Acceleration for Deep Neural Networkscited by 301
  24. 2020Equalization Loss for Long-Tailed Object Recognitioncited by 285
  25. 2014Speeding up Convolutional Neural Networks with Low Rank Expansionscited by 284
  26. 2020Personalized Cross-Silo Federated Learning on Non-IID Datacited by 283
  27. 2020MCUNet: Tiny Deep Learning on IoT Devicescited by 273
  28. 2018Fast Online Object Tracking and Segmentation: A Unifying Approachcited by 272
  29. 2019Asynchronous Federated Optimizationcited by 267
  30. 2019Random Search and Reproducibility for Neural Architecture Searchcited by 254
  31. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 252
  32. 2021Exploring Cross-Image Pixel Contrast for Semantic Segmentationcited by 242
  33. 2019Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computingcited by 228
  34. 2016Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architecturescited by 221
  35. 2017The Reversible Residual Network: Backpropagation Without Storing Activationscited by 217
  36. 2015Quantized Convolutional Neural Networks for Mobile Devicescited by 215
  37. 2014Compressing Deep Convolutional Networks using Vector Quantizationcited by 195
  38. 2017Hierarchical Representations for Efficient Architecture Searchcited by 191

50 most cited of 157 All 157 (JSON)

Built on by

Cited by year

Citing papers per year: 2024: 7; 2025: 1.

8 papers.

  1. 2025SURGEON: Memory-Adaptive Fully Test-Time Adaptation via Dynamic Activation Sparsitycited by 7
  2. 2024Integer-only Quantized Transformers for Embedded FPGA-based Time-series Forecasting in AIoTcited by 6
  3. 2024Generative AI for Low-Carbon Artificial Intelligence of Things with Large Language Modelscited by 3
  4. 2024Combining Federated Learning and Control: A Surveycited by 3
  5. 2024AdaFlow: Opportunistic Inference on Asynchronous Mobile Data with Generalized Affinity Controlcited by 2
  6. 2024AdaShadow: Responsive Test-time Model Adaptation in Non-stationary Mobile Environmentscited by 1
  7. 2024AdaScale: Dynamic Context-aware DNN Scaling via Automated Adaptation Loop on Mobile Devicescited by 1
  8. 2024CrowdTransfer: Enabling Crowd Knowledge Transfer in AIoT Communitycited by 0