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

Showing 201250 of 534 papers

TitleStatusHype
Network Compression via Central FilterCode0
Quantum-Inspired Hamiltonian Monte Carlo for Bayesian SamplingCode0
Magnitude and Similarity based Variable Rate Filter Pruning for Efficient Convolution Neural NetworksCode0
DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy CompressionCode0
“Learning-Compression” Algorithms for Neural Net PruningCode0
FALCON: FLOP-Aware Combinatorial Optimization for Neural Network PruningCode0
Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman CodingCode0
LLM-Rank: A Graph Theoretical Approach to Pruning Large Language ModelsCode0
FastDepth: Fast Monocular Depth Estimation on Embedded SystemsCode0
Learning Sparse Networks Using Targeted DropoutCode0
Self-supervised Feature-Gate Coupling for Dynamic Network PruningCode0
Feature Selection for Multivariate Time Series via Network PruningCode0
Class-dependent Compression of Deep Neural NetworksCode0
Scaling Up Semi-supervised Learning with Unconstrained Unlabelled DataCode0
Less is KEN: a Universal and Simple Non-Parametric Pruning Algorithm for Large Language ModelsCode0
Lost in Pruning: The Effects of Pruning Neural Networks beyond Test AccuracyCode0
Knowledge-Enhanced Semi-Supervised Federated Learning for Aggregating Heterogeneous Lightweight Clients in IoTCode0
L-CO-Net: Learned Condensation-Optimization Network for Clinical Parameter Estimation from Cardiac Cine MRICode0
Cross-Model Comparative Loss for Enhancing Neuronal Utility in Language UnderstandingCode0
Few Sample Knowledge Distillation for Efficient Network CompressionCode0
LEAN: graph-based pruning for convolutional neural networks by extracting longest chainsCode0
Iterative Network Pruning with Uncertainty Regularization for Lifelong Sentiment ClassificationCode0
Attention-Based Guided Structured Sparsity of Deep Neural NetworksCode0
Investigating the Effect of Network Pruning on Performance and InterpretabilityCode0
Is Complexity Required for Neural Network Pruning? A Case Study on Global Magnitude PruningCode0
Rethinking Weight Decay For Efficient Neural Network PruningCode0
A Framework for Neural Network Pruning Using Gibbs DistributionsCode0
Continual Learning for Task-oriented Dialogue System with Iterative Network Pruning, Expanding and MaskingCode0
Stabilizing Elastic Weight Consolidation method in practical ML tasks and using weight importances for neural network pruningCode0
ST-MFNet Mini: Knowledge Distillation-Driven Frame InterpolationCode0
Global Magnitude Pruning With Minimum Threshold Is All We NeedCode0
Connectivity Matters: Neural Network Pruning Through the Lens of Effective SparsityCode0
Aggressive or Imperceptible, or Both: Network Pruning Assisted Hybrid Byzantines in Federated LearningCode0
Compact Bayesian Neural Networks via pruned MCMC samplingCode0
Interpretations Steered Network Pruning via Amortized Inferred Saliency MapsCode0
Importance Estimation for Neural Network PruningCode0
A Fair Loss Function for Network PruningCode0
Improving Generalization in Meta-Learning via Meta-Gradient AugmentationCode0
Compression-aware Training of Neural Networks using Frank-WolfeCode0
A Systematic DNN Weight Pruning Framework using Alternating Direction Method of MultipliersCode0
Improving the Transferability of Adversarial Examples via Direction TuningCode0
Efficient Structured Pruning and Architecture Searching for Group ConvolutionCode0
Network Pruning via Feature Shift MinimizationCode0
Comprehensive Study on Performance Evaluation and Optimization of Model Compression: Bridging Traditional Deep Learning and Large Language Models0
Comprehensive Online Network Pruning via Learnable Scaling Factors0
A Survey on Deep Neural Network Compression: Challenges, Overview, and Solutions0
Hyperpruning: Efficient Search through Pruned Variants of Recurrent Neural Networks Leveraging Lyapunov Spectrum0
Composition of Saliency Metrics for Channel Pruning with a Myopic Oracle0
Hyperparameter Optimization with Neural Network Pruning0
Hyperflows: Pruning Reveals the Importance of Weights0
Show:102550
← PrevPage 5 of 11Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1ResNet50-2.3 GFLOPsAccuracy78.79Unverified
2ResNet50-1.5 GFLOPsAccuracy78.07Unverified
3ResNet50 2.5 GFLOPSAccuracy78Unverified
4RegX-1.6GAccuracy77.97Unverified
5ResNet50 2.0 GFLOPSAccuracy77.7Unverified
6ResNet50-3G FLOPsAccuracy77.1Unverified
7ResNet50-2G FLOPsAccuracy76.4Unverified
8ResNet50-1G FLOPsAccuracy76.38Unverified
9TAS-pruned ResNet-50Accuracy76.2Unverified
10ResNet50Accuracy75.59Unverified
#ModelMetricClaimedVerifiedStatus
1FeatherTop-1 Accuracy76.93Unverified
2SpartanTop-1 Accuracy76.17Unverified
3ST-3Top-1 Accuracy76.03Unverified
4AC/DCTop-1 Accuracy75.64Unverified
5CSTop-1 Accuracy75.5Unverified
6ProbMaskTop-1 Accuracy74.68Unverified
7STRTop-1 Accuracy74.31Unverified
8DNWTop-1 Accuracy74Unverified
9GMPTop-1 Accuracy73.91Unverified
#ModelMetricClaimedVerifiedStatus
1+U-DML*Inference Time (ms)675.56Unverified
2DenseAccuracy79Unverified
3AC/DCAccuracy78.2Unverified
4Beta-RankAccuracy74.01Unverified
5TAS-pruned ResNet-110Accuracy73.16Unverified
#ModelMetricClaimedVerifiedStatus
1TAS-pruned ResNet-110Accuracy94.33Unverified
2ShuffleNet – QuantisedInference Time (ms)23.15Unverified
3AlexNet – QuantisedInference Time (ms)5.23Unverified
4MobileNet – QuantisedInference Time (ms)4.74Unverified
#ModelMetricClaimedVerifiedStatus
1FFN-ShapleyPrunedAvg #Steps12.05Unverified