SOTAVerified

Network Pruning

Network Pruning is a popular approach to reduce a heavy network to obtain a light-weight form by removing redundancy in the heavy network. In this approach, a complex over-parameterized network is first trained, then pruned based on come criterions, and finally fine-tuned to achieve comparable performance with reduced parameters.

Source: Ensemble Knowledge Distillation for Learning Improved and Efficient Networks

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 51–100 of 534 papers

TitleStatusHype
Effective Subset Selection Through The Lens of Neural Network Pruning—0
Finding Lottery Tickets in Vision Models via Data-driven Spectral Foresight PruningCode1
Deep Network Pruning: A Comparative Study on CNNs in Face Recognition—0
A rescaling-invariant Lipschitz bound based on path-metrics for modern ReLU network parameterizations—0
Dependency-Aware Semi-Structured Sparsity of GLU Variants in Large Language Models—0
FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity—0
Adversarial Robustness of Distilled and Pruned Deep Learning-based Wireless Classifiers—0
Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated LearningCode0
FedMef: Towards Memory-efficient Federated Dynamic Pruning—0
Auto-Train-Once: Controller Network Guided Automatic Network Pruning from ScratchCode1
LNPT: Label-free Network Pruning and Training—0
Adversarial Fine-tuning of Compressed Neural Networks for Joint Improvement of Robustness and EfficiencyCode0
FALCON: FLOP-Aware Combinatorial Optimization for Neural Network PruningCode0
Pruning neural network models for gene regulatory dynamics using data and domain knowledgeCode0
Structurally Prune Anything: Any Architecture, Any Framework, Any Time—0
SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization—0
What to Do When Your Discrete Optimization Is the Size of a Neural Network?Code0
Discriminative Adversarial Unlearning—0
Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language ModelsCode0
EPSD: Early Pruning with Self-Distillation for Efficient Model Compression—0
Enhancing Scalability in Recommender Systems through Lottery Ticket Hypothesis and Knowledge Distillation-based Neural Network Pruning—0
GD doesn't make the cut: Three ways that non-differentiability affects neural network training—0
Device-Wise Federated Network PruningCode0
Block Pruning for Enhanced Efficiency in Convolutional Neural Networks—0
Fluctuation-based Adaptive Structured Pruning for Large Language ModelsCode1
Picking the Underused Heads: A Network Pruning Perspective of Attention Head Selection for Fusing Dialogue Coreference Information—0
Neural Architecture Codesign for Fast Bragg Peak Analysis—0
Accelerating Convolutional Neural Network Pruning via Spatial Aura Entropy—0
An End-to-End Network Pruning Pipeline with Sparsity Enforcement—0
Towards Higher Ranks via Adversarial Weight PruningCode0
LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPSCode2
Filter-Pruning of Lightweight Face Detectors Using a Geometric Median CriterionCode1
Robustness-Reinforced Knowledge Distillation with Correlation Distance and Network Pruning—0
Neural Network Pruning by Gradient DescentCode0
Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks—0
Data Augmentations in Deep Weight Spaces—0
Do Localization Methods Actually Localize Memorized Data in LLMs? A Tale of Two BenchmarksCode0
Beyond Size: How Gradients Shape Pruning Decisions in Large Language ModelsCode1
Brain-Inspired Efficient Pruning: Exploiting Criticality in Spiking Neural Networks—0
Efficient Model-Based Deep Learning via Network Pruning and Fine-TuningCode0
Importance Estimation with Random Gradient for Neural Network Pruning—0
SparseByteNN: A Novel Mobile Inference Acceleration Framework Based on Fine-Grained Group SparsityCode0
Linear Mode Connectivity in Sparse Neural Networks—0
GraFT: Gradual Fusion Transformer for Multimodal Re-Identification—0
Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMsCode1
Samples on Thin Ice: Re-Evaluating Adversarial Pruning of Neural Networks—0
Filter Pruning For CNN With Enhanced Linear Representation RedundancyCode0
Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High SparsityCode1
SWAP: Sparse Entropic Wasserstein Regression for Robust Network PruningCode0
Feather: An Elegant Solution to Effective DNN SparsificationCode1
Show:102550
← PrevPage 2 of 11Next →
All datasetsImageNetImageNet - ResNet 50 - 90% sparsityCIFAR-100CIFAR-10MNIST

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50-2.3 GFLOPsAccuracy78.79—Unverified
2ResNet50-1.5 GFLOPsAccuracy78.07—Unverified
3ResNet50 2.5 GFLOPSAccuracy78—Unverified
4RegX-1.6GAccuracy77.97—Unverified
5ResNet50 2.0 GFLOPSAccuracy77.7—Unverified
6ResNet50-3G FLOPsAccuracy77.1—Unverified
7ResNet50-2G FLOPsAccuracy76.4—Unverified
8ResNet50-1G FLOPsAccuracy76.38—Unverified
9TAS-pruned ResNet-50Accuracy76.2—Unverified
10ResNet50Accuracy75.59—Unverified
#ModelMetricClaimedVerifiedStatus
1FeatherTop-1 Accuracy76.93—Unverified
2SpartanTop-1 Accuracy76.17—Unverified
3ST-3Top-1 Accuracy76.03—Unverified
4AC/DCTop-1 Accuracy75.64—Unverified
5CSTop-1 Accuracy75.5—Unverified
6ProbMaskTop-1 Accuracy74.68—Unverified
7STRTop-1 Accuracy74.31—Unverified
8DNWTop-1 Accuracy74—Unverified
9GMPTop-1 Accuracy73.91—Unverified
#ModelMetricClaimedVerifiedStatus
1+U-DML*Inference Time (ms)675.56—Unverified
2DenseAccuracy79—Unverified
3AC/DCAccuracy78.2—Unverified
4Beta-RankAccuracy74.01—Unverified
5TAS-pruned ResNet-110Accuracy73.16—Unverified
#ModelMetricClaimedVerifiedStatus
1TAS-pruned ResNet-110Accuracy94.33—Unverified
2ShuffleNet – QuantisedInference Time (ms)23.15—Unverified
3AlexNet – QuantisedInference Time (ms)5.23—Unverified
4MobileNet – QuantisedInference Time (ms)4.74—Unverified
#ModelMetricClaimedVerifiedStatus
1FFN-ShapleyPrunedAvg #Steps12.05—Unverified