YongHuaZhang-BUAA / awesome-pruning-acceleration

Incredible acceleration with pruning or the other compression techniques

awesome-pruning-acceleration

Hello visitors, I have been interested in an efficient deep neural network design, such as pruning, AutoML, quantization, and focused on the knowledge distillation for successful network generalization. This page organizes for pruning.

History

• 2021 years
• 2020 years
• 2019 years
• 2018 years
• 2017 years
• 2016 years
• 2015 years

2021

Title	Issue	Release
Dynamic Slimmable Network	CVPR	GitHub
Robust Pruning at Initialization	ICLR	-

2020

Title	Issue	Release
What is the State of Neural Network Pruning?	MLSys	GitHub
The Generalization-Stability Tradeoff In Neural Network Pruning	NeurIPS	GitHub
Position-based Scaled Gradient for Model Quantization and Pruning	NeurIPS	GitHub
Sanity-Checking Pruning Methods: Random Tickets can Win the Jackpot	NeurIPS	GitHub
Movement Pruning: Adaptive Sparsity by Fine-Tuning	NeurIPS	GitHub
HYDRA: Pruning Adversarially Robust Neural Networks	NeurIPS	GitHub
Pruning Filter in Filter	NeurIPS	GitHub
Storage Efficient and Dynamic Flexible Runtime Channel Pruning via Deep Reinforcement Learning	NeurIPS	GitHub
Directional Pruning of Deep Neural Networks	NeurIPS	GitHub
SCOP: Scientific Control for Reliable Neural Network Pruning	NeurIPS	-
Neuron-level Structured Pruning using Polarization Regularizer	NeurIPS	GitHub
Pruning neural networks without any data by iteratively conserving synaptic flow	NeurIPS	GitHub
Neuron Merging: Compensating for Pruned Neurons	NeurIPS	GitHub
Filter Pruning and Re-Initialization via Latent Space Clustering	IEEE Access	-
TF-NAS: Rethinking Three Search Freedoms of Latency-Constrained Differentiable Neural Architecture Search	ECCV	GitHub
Differentiable Joint Pruning and Quantization for Hardware Efficiency	ECCV	-
DA-NAS: Data Adapted Pruning for Efficient Neural Architecture Search	ECCV	-
Accelerating CNN Training by Pruning Activation Gradients	ECCV	-
DHP: Differentiable Meta Pruning via HyperNetworks	ECCV	GitHub
DSA: More Efficient Budgeted Pruning via Differentiable Sparsity Allocation	ECCV	GitHub
EagleEye: Fast Sub-net Evaluation for Efficient Neural Network Pruning	ECCV	GitHub
PCONV: The Missing but Desirable Sparsity in DNN Weight Pruning for Real-time Execution on Mobile Devices	AAAI	-
Dynamic Network Pruning with Interpretable Layerwise Channel Selection	AAAI	-
Reborn Filters: Pruning Convolutional Neural Networks with Limited Data	AAAI	-
Channel Pruning Guided by Classification Loss and Feature Importance	AAAI	-
Pruning from Scratch	AAAI	-
DropNet: Reducing Neural Network Complexity via Iterative Pruning	ICML	GitHub
Operation-Aware Soft Channel Pruning using Differentiable Masks	ICML	-
Group Sparsity: The Hinge Between Filter Pruning and Decomposition for Network Compression	CVPR	GitHub
APQ: Joint Search for Network Architecture, Pruning and Quantization Policy	CVPR	-
Learning Filter Pruning Criteria for Deep Convolutional Neural Networks Acceleration	CVPR	-
Structured Compression by Weight Encryption for Unstructured Pruning and Quantization	CVPR	-
Multi-Dimensional Pruning: A Unified Framework for Model Compression	CVPR	-
DMCP: Differentiable Markov Channel Pruning for Neural Networks	CVPR	-
HRank: Filter Pruning using High-Rank Feature Map	CVPR	GitHub
Neural Network Pruning with Residual-Connections and Limited-Data	CVPR	-
Picking Winning Tickets Before Training by Preserving Gradient Flow	ICLR	GitHub
Provable Filter Pruning for Efficient Neural Networks	ICLR	GitHub
Data-Independent Neural Pruning via Coresets	ICLR	-
Lookahead: A Far-sighted Alternative of Magnitude-based Pruning	ICLR	GitHub
Dynamic Model Pruning with Feedback	ICLR	-
One-shot Pruning of Recurrent Neural Neworks by Jacobian Spectrum Evaluation	ICLR	-
A Signal Propagation Perspective for Pruning Neural Networks at Initialization	ICLR	GitHub

2019

Title	Issue	Release
MetaPruning: Meta Learning for Automatic Neural Network Channel Pruning	ICCV	GitHub
Variational Convolutional Neural Network Pruning	CVPR	-
Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration	CVPR	GitHub
Towards Optimal Structured CNN Pruning via Generative Adversarial Learning (GAL)	CVPR	GitHub
Network Pruning via Transformable Architecture Search	NeurIPS	GitHub
Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networks	NeurIPS	GitHub
Global Sparse Momentum SGD for Pruning Very Deep Neural Networks	NeurIPS	GitHub
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks	ICLR	-
Integral Pruning on Activations and Weights for Efficient Neural Networks	ICLR	-
SNIP: Single-Shot Network Pruning Based on Connection Sensitivity	ICLR	GitHub

2018

Title	Issue	Release
Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layers	ICLR	GitHub
Clustering Convolutional Kernels to Compress Deep Neural Networks	ECCV	GitHub
NISP: Pruning Networks using Neuron Importance Score Propagation	CVPR	-
Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks	IJCAI	GitHub
Accelerating convolutional networks via global & dynamic filter pruning	IJCAI	-

2017

Title	Issue	Release
Pruning Filters for Efficient ConvNets	ICLR	GitHub
Pruning Convolutional Neural Networks for Resource Efficient Inference	ICLR	GitHub
Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruning	CVPR	-
ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression	ICCV	GitHub
Channel pruning for accelerating very deep neural networks	ICCV	GitHub
Learning Efficient Convolutional Networks Through Network Slimming	ICCV	GitHub
Scalpel: Customizing DNN Pruning to the Underlying Hardware Parallelism	ISCA	GitHub

2016

Title	Issue	Release
Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding	ICLR	-
Eyeriss: A Spatial Architecture for Energy-Efficient Dataflow for Convolutional Neural Networks	ISCA	-

2015

Title	Issue	Release
Learning both Weights and Connections for Efficient Neural Networks	NeurIPS	-