mlsanityData to 7 Oct 2026

A Survey on Methods and Theories of Quantized Neural Networks

arXiv 1808.04752 ↗First posted 13 Aug 2018cs.LG cs.NE stat.MLcited by 75

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are the state-of-the-art methods for many real-world tasks, such as computer vision, natural language processing and speech recognition. For all its popularity, deep neural networks are also criticized for consuming a lot of memory and draining battery life of devices during training and inference. This makes it hard to deploy these models on mobile or embedded devices which have tight resource constraints. Quantization is recognized as one of the most effective approaches to satisfy the extreme memory requirements that deep neural network models demand. Instead of adopting 32-bit floating point format to represent weights, quantized representations store weights using more compact formats such as integers or even binary numbers. Despite a possible degradation in predictive performance, quantization provides a potential solution to greatly reduce the model size and the energy consumption. In this survey, we give a thorough review of different aspects of quantized neural networks. Current challenges and trends of quantized neural networks are also discussed.

Key facts. Cited by 75 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 21; 2022: 16; 2023: 16; 2024: 8; 2025: 11; 2026: 3.

75 papers.

Sort:

By area:

  1. 2021Pruning and Quantization for Deep Neural Network Acceleration: A Surveycited by 259
  2. 2023Structured Pruning for Deep Convolutional Neural Networks: A surveycited by 122
  3. 2022A Comprehensive Survey on Model Quantization for Deep Neural Networks in Image Classificationcited by 64
  4. 2021Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimizationcited by 57
  5. 2022Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networkscited by 55
  6. 2021A Survey on Green Deep Learningcited by 52
  7. 2021Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safetycited by 35
  8. 2021A Review on Deep Learning in UAV Remote Sensingcited by 32
  9. 2022Post-training Quantization for Neural Networks with Provable Guaranteescited by 32
  10. 2023LLaMAntino: LLaMA 2 Models for Effective Text Generation in Italian Languagecited by 24
  11. 2021On the Adversarial Robustness of Quantized Neural Networkscited by 11
  12. 2021Demystifying and Generalizing BinaryConnectcited by 11
38 more
  1. 2021AdaSTE: An Adaptive Straight-Through Estimator to Train Binary Neural Networkscited by 11
  2. 2021Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latencycited by 9
  3. 2023Efficient Neural Networks for Tiny Machine Learning: A Comprehensive Reviewcited by 9
  4. 2024Q-S5: Towards Quantized State Space Modelscited by 9
  5. 2021Fixed-point Quantization of Convolutional Neural Networks for Quantized Inference on Embedded Platformscited by 7
  6. 2022CoCoFL: Communication- and Computation-Aware Federated Learning via Partial NN Freezing and Quantizationcited by 7
  7. 2022Mixed-Precision Neural Networks: A Surveycited by 7
  8. 2022A simple approach for quantizing neural networkscited by 7
  9. 2025A quantitative analysis of semantic information in deep representations of text and imagescited by 7
  10. 2021Random and Adversarial Bit Error Robustness: Energy-Efficient and Secure DNN Acceleratorscited by 6
  11. 2021Verifying Quantized Neural Networks using SMT-Based Model Checkingcited by 6
  12. 2022Survey: Exploiting Data Redundancy for Optimization of Deep Learningcited by 6
  13. 2022Personalized Federated Learning with Communication Compressioncited by 6
  14. 2021Using Neighborhood Context to Improve Information Extraction from Visual Documents Captured on Mobile Phonescited by 5
  15. 2023Towards Efficient In-memory Computing Hardware for Quantized Neural Networks: State-of-the-art, Open Challenges and Perspectivescited by 5
  16. 2021Multiplierless MP-Kernel Machine For Energy-efficient Edge Devicescited by 4
  17. 2021QNNVerifier: A Tool for Verifying Neural Networks using SMT-Based Model Checkingcited by 4
  18. 2021Approximation of functions with one-bit neural networkscited by 4
  19. 2023Number Systems for Deep Neural Network Architectures: A Surveycited by 4
  20. 2025Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrievalcited by 4
  21. 2021Activation Density based Mixed-Precision Quantization for Energy Efficient Neural Networkscited by 3
  22. 2021BitTrain: Sparse Bitmap Compression for Memory-Efficient Training on the Edgecited by 3
  23. 2022SAMP: A Model Inference Toolkit of Post-Training Quantization for Text Processing via Self-Adaptive Mixed-Precisioncited by 3
  24. 2023LinguaLinked: A Distributed Large Language Model Inference System for Mobile Devicescited by 3
  25. 2024Building an Efficient Multilingual Non-Profit IR System for the Islamic Domain Leveraging Multiprocessing Design in Rustcited by 3
  26. 2022AskewSGD : An Annealed interval-constrained Optimisation method to train Quantized Neural Networkscited by 2
  27. 2023Gated Compression Layers for Efficient Always-On Modelscited by 2
  28. 2023Deploying Deep Reinforcement Learning Systems: A Taxonomy of Challengescited by 2
  29. 2024From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networkscited by 2
  30. 2024Unsupervised detection of semantic correlations in big datacited by 2
  31. 2025On the Privacy-Preserving Properties of Spiking Neural Networks with Unique Surrogate Gradients and Quantization Levelscited by 2
  32. 2025Stochastic Weight Sharing for Bayesian Neural Networkscited by 2
  33. 2026Towards Understanding Best Practices for Quantization of Vision-Language Modelscited by 2
  34. 2021Smoothed Differential Privacycited by 1
  35. 2021Differentiable Architecture Pruning for Transfer Learningcited by 1
  36. 2022AutoDiCE: Fully Automated Distributed CNN Inference at the Edgecited by 1
  37. 2022Going Further With Winograd Convolutions: Tap-Wise Quantization for Efficient Inference on 4x4 Tilecited by 1
  38. 2022EuclidNets: An Alternative Operation for Efficient Inference of Deep Learning Modelscited by 1

50 most cited of 75 All 75 (JSON)