mlsanityData to 7 Oct 2026

AutoMC: Automated Model Compression based on Domain Knowledge and Progressive search strategy

arXiv 2201.09884 ↗First posted 24 Jan 2022cs.LG cs.AI cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Model compression methods can reduce model complexity on the premise of maintaining acceptable performance, and thus promote the application of deep neural networks under resource constrained environments. Despite their great success, the selection of suitable compression methods and design of details of the compression scheme are difficult, requiring lots of domain knowledge as support, which is not friendly to non-expert users. To make more users easily access to the model compression scheme that best meet their needs, in this paper, we propose AutoMC, an effective automatic tool for model compression. AutoMC builds the domain knowledge on model compression to deeply understand the characteristics and advantages of each compression method under different settings. In addition, it presents a progressive search strategy to efficiently explore pareto optimal compression scheme according to the learned prior knowledge combined with the historical evaluation information. Extensive experimental results show that AutoMC can provide satisfying compression schemes within short time, demonstrating the effectiveness of AutoMC.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 24 of its 50 references that are in the map. First posted on arXiv 24 Jan 2022.

Builds on

24 of 50 references.

References · 24

  1. 2018DARTS: Differentiable Architecture Searchcited by 1,782
  2. 2017Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inferencecited by 1,548
  3. 2018Regularized Evolution for Image Classifier Architecture Searchcited by 902
  4. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  5. 2018Soft Filter Pruning for Accelerating Deep Convolutional Neural Networkscited by 313
  6. 2019MetaPruning: Meta Learning for Automatic Neural Network Channel Pruningcited by 226
  7. 2017Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weightscited by 211
  8. 2019Deep Learning for Spatio-Temporal Data Mining: A Surveycited by 171
  9. 2019Towards Optimal Structured CNN Pruning via Generative Adversarial Learningcited by 145
  10. 2017MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networkscited by 92
  11. 2017Neural Optimizer Search with Reinforcement Learningcited by 82
  12. 2019Towards Efficient Model Compression via Learned Global Rankingcited by 75
12 more
  1. 2019Learning Filter Basis for Convolutional Neural Network Compressioncited by 57
  2. 2020AdaBERT: Task-Adaptive BERT Compression with Differentiable Neural Architecture Searchcited by 51
  3. 2018Exploiting Kernel Sparsity and Entropy for Interpretable CNN Compressioncited by 40
  4. 2018Deep Air Quality Forecasting Using Hybrid Deep Learning Frameworkcited by 33
  5. 2016Towards Better Exploiting Convolutional Neural Networks for Remote Sensing Scene Classificationcited by 29
  6. 2019ASAP: Architecture Search, Anneal and Prunecited by 29
  7. 2019DeepLine: AutoML Tool for Pipelines Generation using Deep Reinforcement Learning and Hierarchical Actions Filteringcited by 21
  8. 2020Warm Starting CMA-ES for Hyperparameter Optimizationcited by 18
  9. 2019Meta-Surrogate Benchmarking for Hyperparameter Optimizationcited by 16
  10. 2021COMET: A Novel Memory-Efficient Deep Learning Training Framework by Using Error-Bounded Lossy Compressioncited by 8
  11. 2019Progressive Compressed Records: Taking a Byte out of Deep Learning Datacited by 4
  12. 2019Light Multi-segment Activation for Model Compressioncited by 1

Built on by

Not cited yet.