# All-in-One: A Highly Representative DNN Pruning Framework for Edge Devices with Dynamic Power Management arXiv: https://arxiv.org/abs/2212.05122 ยท HTML: https://mlsanity.com/paper/2212.05122/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Builds on 35 of its 41 references that are in the map. - First posted on arXiv 9 Dec 2022. ## Builds on (most cited first, 30 of 35) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015) - [Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computation](https://mlsanity.com/paper/1308.3432/) (2013) - [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015) - [YOLOv4: Optimal Speed and Accuracy of Object Detection](https://mlsanity.com/paper/2004.10934/) (2020) - [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019) - [Channel Pruning for Accelerating Very Deep Neural Networks](https://mlsanity.com/paper/1707.06168/) (2017) - [Learning Structured Sparsity in Deep Neural Networks](https://mlsanity.com/paper/1608.03665/) (2016) - [AMC: AutoML for Model Compression and Acceleration on Mobile Devices](https://mlsanity.com/paper/1802.03494/) (2018) - [Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration](https://mlsanity.com/paper/1811.00250/) (2018) - [Slimmable Neural Networks](https://mlsanity.com/paper/1812.08928/) (2018) - [Dynamic Network Surgery for Efficient DNNs](https://mlsanity.com/paper/1608.04493/) (2016) - [Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets](https://mlsanity.com/paper/1903.05662/) (2019) - [Universally Slimmable Networks and Improved Training Techniques](https://mlsanity.com/paper/1903.05134/) (2019) - [Discrimination-aware Channel Pruning for Deep Neural Networks](https://mlsanity.com/paper/1810.11809/) (2018) - [MEST: Accurate and Fast Memory-Economic Sparse Training Framework on the Edge](https://mlsanity.com/paper/2110.14032/) (2021) - [PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning](https://mlsanity.com/paper/2001.00138/) (2020) - [DMCP: Differentiable Markov Channel Pruning for Neural Networks](https://mlsanity.com/paper/2005.03354/) (2020) - [PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices](https://mlsanity.com/paper/1909.05073/) (2019) - [AutoCompress: An Automatic DNN Structured Pruning Framework for Ultra-High Compression Rates](https://mlsanity.com/paper/1907.03141/) (2019) - [Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search](https://mlsanity.com/paper/2108.08910/) (2021) - [DAIS: Automatic Channel Pruning via Differentiable Annealing Indicator Search](https://mlsanity.com/paper/2011.02166/) (2020) - [Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution](https://mlsanity.com/paper/2207.12577/) (2022) - [RTMobile: Beyond Real-Time Mobile Acceleration of RNNs for Speech Recognition](https://mlsanity.com/paper/2002.11474/) (2020) - [Learning low-precision neural networks without Straight-Through Estimator(STE)](https://mlsanity.com/paper/1903.01061/) (2019) - [2PFPCE: Two-Phase Filter Pruning Based on Conditional Entropy](https://mlsanity.com/paper/1809.02220/) (2018) - [A Privacy-Preserving-Oriented DNN Pruning and Mobile Acceleration Framework](https://mlsanity.com/paper/2003.06513/) (2020) - [Tiny but Accurate: A Pruned, Quantized and Optimized Memristor Crossbar Framework for Ultra Efficient DNN Implementation](https://mlsanity.com/paper/1908.10017/) (2019) - [Dancing along Battery: Enabling Transformer with Run-time Reconfigurability on Mobile Devices](https://mlsanity.com/paper/2102.06336/) (2021) - [SS-Auto: A Single-Shot, Automatic Structured Weight Pruning Framework of DNNs with Ultra-High Efficiency](https://mlsanity.com/paper/2001.08839/) (2020) ## Built on by (most cited first, 5 of 5) - [Exploring Token Pruning in Vision State Space Models](https://mlsanity.com/paper/2409.18962/) (2024) - [Numerical Pruning for Efficient Autoregressive Models](https://mlsanity.com/paper/2412.12441/) (2024) - [AdaPI: Facilitating DNN Model Adaptivity for Efficient Private Inference in Edge Computing](https://mlsanity.com/paper/2407.05633/) (2024) - [AyE-Edge: Automated Deployment Space Search Empowering Accuracy yet Efficient Real-Time Object Detection on the Edge](https://mlsanity.com/paper/2408.05363/) (2024) - [Lotus: learning-based online thermal and latency variation management for two-stage detectors on edge devices](https://mlsanity.com/paper/2410.10847/) (2024) ## Abstract (arXiv) During the deployment of deep neural networks (DNNs) on edge devices, many research efforts are devoted to the limited hardware resource. However, little attention is paid to the influence of dynamic power management. As edge devices typically only have a budget of energy with batteries (rather than almost unlimited energy support on servers or workstations), their dynamic power management often changes the execution frequency as in the widely-used dynamic voltage and frequency scaling (DVFS) technique. This leads to highly unstable inference speed performance, especially for computation-intensive DNN models, which can harm user experience and waste hardware resources. We firstly identify this problem and then propose All-in-One, a highly representative pruning framework to work with dynamic power management using DVFS. The framework can use only one set of model weights and soft masks (together with other auxiliary parameters of negligible storage) to represent multiple models of various pruning ratios. By re-configuring the model to the corresponding pruning ratio for a specific execution frequency (and voltage), we are able to achieve stable inference speed, i.e., keeping the difference in speed performance under various execution frequencies as small as possible. Our experiments demonstrate that our method not only achieves high accuracy for multiple models of different pruning ratios, but also reduces their variance of inference latency for various frequencies, with minimal memory consumption of only one model and one soft mask.