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 101–150 of 534 papers

TitleStatusHype
Discrimination-aware Network Pruning for Deep Model CompressionCode1
Discovering Neural WiringsCode1
Dynamic Channel Pruning: Feature Boosting and SuppressionCode1
SNIP: Single-shot Network Pruning based on Connection SensitivityCode1
Channel Gating Neural NetworksCode1
The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural NetworksCode1
PackNet: Adding Multiple Tasks to a Single Network by Iterative PruningCode1
SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model sizeCode1
Hyperpruning: Efficient Search through Pruned Variants of Recurrent Neural Networks Leveraging Lyapunov Spectrum—0
TSENOR: Highly-Efficient Algorithm for Finding Transposable N:M Sparse Masks—0
Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language ModelsCode0
Adaptive Pruning of Deep Neural Networks for Resource-Aware Embedded Intrusion Detection on the EdgeCode0
Bi-LSTM based Multi-Agent DRL with Computation-aware Pruning for Agent Twins Migration in Vehicular Embodied AI Networks—0
Guiding Evolutionary AutoEncoder Training with Activation-Based Pruning OperatorsCode0
Optimization over Trained (and Sparse) Neural Networks: A Surrogate within a Surrogate—0
Hyperflows: Pruning Reveals the Importance of Weights—0
Boosting Large Language Models with Mask Fine-TuningCode0
Lipschitz Constant Meets Condition Number: Learning Robust and Compact Deep Neural Networks—0
Maximum Redundancy Pruning: A Principle-Driven Layerwise Sparsity Allocation for LLMs—0
Finding Stable Subnetworks at Initialization with Dataset Distillation—0
Multi-Agent Actor-Critic with Harmonic Annealing Pruning for Dynamic Spectrum Access Systems—0
Signal Collapse in One-Shot Pruning: When Sparse Models Fail to Distinguish Neural Representations—0
NTP-INT: Network Traffic Prediction-Driven In-band Network Telemetry for High-load Switches—0
An Efficient Row-Based Sparse Fine-Tuning—0
Automatic Pruning via Structured Lasso with Class-wise Information—0
Exploring Neural Network Pruning with Screening Methods—0
B-FPGM: Lightweight Face Detection via Bayesian-Optimized Soft FPGM PruningCode0
Compact Bayesian Neural Networks via pruned MCMC samplingCode0
Neural Architecture Codesign for Fast Physics ApplicationsCode0
Scalable iterative pruning of large language and vision models using block coordinate descent—0
Adapting the Biological SSVEP Response to Artificial Neural Networks—0
Complexity-Aware Training of Deep Neural Networks for Optimal Structure Discovery—0
Zeroth-Order Adaptive Neuron Alignment Based Pruning without Re-TrainingCode0
Mutual Information Preserving Neural Network Pruning—0
Small Contributions, Small Networks: Efficient Neural Network Pruning Based on Relative Importance—0
LLM-Rank: A Graph Theoretical Approach to Pruning Large Language ModelsCode0
Efficient Multi-Object Tracking on Edge Devices via Reconstruction-Based Channel Pruning—0
Personalized Federated Learning for Generative AI-Assisted Semantic Communications—0
Aggressive Post-Training Compression on Extremely Large Language Models—0
Investigating the Effect of Network Pruning on Performance and InterpretabilityCode0
CFSP: An Efficient Structured Pruning Framework for LLMs with Coarse-to-Fine Activation InformationCode0
3D Point Cloud Network Pruning: When Some Weights Do not MatterCode0
A Greedy Hierarchical Approach to Whole-Network Filter-Pruning in CNNs—0
Confident magnitude-based neural network pruning—0
Mini-batch Coresets for Memory-efficient Training of Large Language Models—0
Comprehensive Study on Performance Evaluation and Optimization of Model Compression: Bridging Traditional Deep Learning and Large Language Models—0
CCSRP: Robust Pruning of Spiking Neural Networks through Cooperative Coevolution—0
Towards Lightweight Graph Neural Network Search with Curriculum Graph Sparsification—0
Finding Task-specific Subnetworks in Multi-task Spoken Language Understanding Model—0
Bypass Back-propagation: Optimization-based Structural Pruning for Large Language Models via Policy Gradient—0
Show:102550
← PrevPage 3 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