mlsanityData to 7 Oct 2026

Enable Deep Learning on Mobile Devices: Methods, Systems, and Applications

arXiv 2204.11786 ↗First posted 25 Apr 2022cs.LG cs.CL cs.CVcited by 32

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) have achieved unprecedented success in the field of artificial intelligence (AI), including computer vision, natural language processing and speech recognition. However, their superior performance comes at the considerable cost of computational complexity, which greatly hinders their applications in many resource-constrained devices, such as mobile phones and Internet of Things (IoT) devices. Therefore, methods and techniques that are able to lift the efficiency bottleneck while preserving the high accuracy of DNNs are in great demand in order to enable numerous edge AI applications. This paper provides an overview of efficient deep learning methods, systems and applications. We start from introducing popular model compression methods, including pruning, factorization, quantization as well as compact model design. To reduce the large design cost of these manual solutions, we discuss the AutoML framework for each of them, such as neural architecture search (NAS) and automated pruning and quantization. We then cover efficient on-device training to enable user customization based on the local data on mobile devices. Apart from general acceleration techniques, we also showcase several task-specific accelerations for point cloud, video and natural language processing by exploiting their spatial sparsity and temporal/token redundancy. Finally, to support all these algorithmic advancements, we introduce the efficient deep learning system design from both software and hardware perspectives.

Key facts. Cited by 32 papers in the map (data through 7 Oct 2026). Builds on 272 of its 372 references that are in the map. First posted on arXiv 25 Apr 2022.

Builds on

272 of 372 references.

References · 272

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  4. 2020Language Models are Few-Shot Learnerscited by 32,199
  5. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  6. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  7. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  8. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  9. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
  10. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  11. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  12. 2018GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understandingcited by 4,854
38 more
  1. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  3. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
  4. 2019DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lightercited by 4,243
  5. 2014Going Deeper with Convolutionscited by 4,231
  6. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,115
  7. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  8. 2020Longformer: The Long-Document Transformercited by 3,362
  9. 2017Quo Vadis, Action Recognition? A New Model and the Kinetics Datasetcited by 3,259
  10. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  11. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,014
  12. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  13. 2015Fast R-CNNcited by 2,930
  14. 2015ShapeNet: An Information-Rich 3D Model Repositorycited by 2,880
  15. 2015Character-level Convolutional Networks for Text Classificationcited by 2,293
  16. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  17. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  18. 2018Dynamic Graph CNN for Learning on Point Cloudscited by 2,220
  19. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,031
  20. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  21. 2019Searching for MobileNetV3cited by 1,984
  22. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  23. 2013Fine-Grained Visual Classification of Aircraftcited by 1,701
  24. 2020Reformer: The Efficient Transformercited by 1,658
  25. 2014FitNets: Hints for Thin Deep Netscited by 1,619
  26. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  27. 2019Generating Long Sequences with Sparse Transformerscited by 1,523
  28. 2016Neural Architecture Search with Reinforcement Learningcited by 1,489
  29. 20163D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotationcited by 1,471
  30. 2020Linformer: Self-Attention with Linear Complexitycited by 1,462
  31. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
  32. 2017VoxelNet: End-to-End Learning for Point Cloud Based 3D Object Detectioncited by 1,323
  33. 2019Energy and Policy Considerations for Deep Learning in NLPcited by 1,242
  34. 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
  35. 20194D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networkscited by 1,201
  36. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,194
  37. 2017A Closer Look at Spatiotemporal Convolutions for Action Recognitioncited by 1,139
  38. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132

50 most cited of 272 All 272 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 11; 2024: 12; 2025: 4; 2026: 2.

32 papers.

Sort:

  1. 2024Fast On-device LLM Inference with NPUscited by 58
  2. 2023LLMCad: Fast and Scalable On-device Large Language Model Inferencecited by 45
  3. 2025Empowering Edge Intelligence: A Comprehensive Survey on On-Device AI Modelscited by 44
  4. 2022A Survey for Efficient Open Domain Question Answeringcited by 20
  5. 2023Towards energy-efficient Deep Learning: An overview of energy-efficient approaches along the Deep Learning Lifecyclecited by 13
  6. 2024Artificial Intelligence of Things: A Surveycited by 12
  7. 2023LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platformscited by 11
  8. 2024Training Machine Learning models at the Edge: A Surveycited by 11
  9. 2024Development of Skip Connection in Deep Neural Networks for Computer Vision and Medical Image Analysis: A Surveycited by 10
  10. 2023PLiNIO: A User-Friendly Library of Gradient-based Methods for Complexity-aware DNN Optimizationcited by 9
  11. 2024Peer-to-Peer Learning Dynamics of Wide Neural Networkscited by 8
  12. 2023Enhancing Neural Architecture Search with Multiple Hardware Constraints for Deep Learning Model Deployment on Tiny IoT Devicescited by 7
20 more
  1. 2024Joint Pruning and Channel-wise Mixed-Precision Quantization for Efficient Deep Neural Networkscited by 6
  2. 2024Efficient Deep Learning Infrastructures for Embedded Computing Systems: A Comprehensive Survey and Future Envisioncited by 5
  3. 2023Peer-to-Peer Deep Learning for Beyond-5G IoTcited by 4
  4. 2022DeepPicarMicro: Applying TinyML to Autonomous Cyber Physical Systemscited by 3
  5. 2022On-Device Domain Generalizationcited by 3
  6. 2023Peer-to-Peer Learning + Consensus with Non-IID Datacited by 3
  7. 2024Momentum Approximation in Asynchronous Private Federated Learningcited by 3
  8. 2025Generative Artificial Intelligence for Internet of Things Computing: A Systematic Surveycited by 3
  9. 2025Energy-Aware Deep Learning on Resource-Constrained Hardwarecited by 3
  10. 2023Memory-aware Scheduling for Complex Wired Networks with Iterative Graph Optimizationcited by 2
  11. 2024Exploring Gen-AI applications in building research and industry: A reviewcited by 2
  12. 2024A Universal Railway Obstacle Detection System based on Semi-supervised Segmentation And Optical Flowcited by 1
  13. 2025Optimizing 3D Gaussian Splattering for Mobile GPUscited by 1
  14. 2023High-Level Parallelism and Nested Features for Dynamic Inference Cost and Top-Down Attentioncited by 0
  15. 2023Neural network scoring for efficient computingcited by 0
  16. 2023Machine learning's own Industrial Revolutioncited by 0
  17. 2024Dynamic DNNs and Runtime Management for Efficient Inference on Mobile/Embedded Devicescited by 0
  18. 2024SPA: Towards A Computational Friendly Cloud-Base and On-Devices Collaboration Seq2seq Personalized Generation with Casual Inferencecited by 0
  19. 2026Uncertainty-Guided Edge Learning for Deep Image Regression in Remote Sensingcited by 0
  20. 2026StreamSplit: Continuous Audio Representation Learning via Uncertainty-Guided Adaptive Splittingcited by 0