Browse > Methodology > Network Pruning

Network Pruning

43 papers with code · Methodology

Leaderboards

Latest papers with code

MicroNet for Efficient Language Modeling

16 May 2020mit-han-lab/neurips-micronet

In this paper, we provide the winning solution to the NeurIPS 2019 MicroNet Challenge in the language modeling track.

LANGUAGE MODELLING MODEL COMPRESSION NETWORK PRUNING QUANTIZATION

7
16 May 2020

Network Adjustment: Channel Search Guided by FLOPs Utilization Ratio

6 Apr 2020danczs/NetworkAdjustment

Automatic designing computationally efficient neural networks has received much attention in recent years.

IMAGE CLASSIFICATION NETWORK PRUNING

3
06 Apr 2020

DHP: Differentiable Meta Pruning via HyperNetworks

30 Mar 2020ofsoundof/dhp

The input of the hypernetwork, namely, the latent vectors control the output channels of the layers of backbone network.

DENOISING IMAGE CLASSIFICATION IMAGE SUPER-RESOLUTION NETWORK PRUNING NEURAL ARCHITECTURE SEARCH

18
30 Mar 2020

What is the State of Neural Network Pruning?

6 Mar 2020jjgo/shrinkbench

Neural network pruning---the task of reducing the size of a network by removing parameters---has been the subject of a great deal of work in recent years.

NETWORK PRUNING

76
06 Mar 2020

Comparing Rewinding and Fine-tuning in Neural Network Pruning

ICLR 2020 lottery-ticket/rewinding-iclr20-public

Learning rate rewinding (which we propose) trains the unpruned weights from their final values using the same learning rate schedule as weight rewinding.

NETWORK PRUNING

32
05 Mar 2020

HRank: Filter Pruning using High-Rank Feature Map

24 Feb 2020lmbxmu/HRank

The principle behind our pruning is that low-rank feature maps contain less information, and thus pruned results can be easily reproduced.

NETWORK PRUNING

55
24 Feb 2020

On Pruning Adversarially Robust Neural Networks

24 Feb 2020inspire-group/compactness-robustness

While the research community has extensively explored the use of robust training and network pruning \emph{independently} to address one of these challenges, we show that integrating existing pruning techniques with multiple types of robust training techniques, including verifiably robust training, leads to poor robust accuracy even though such techniques can preserve high regular accuracy.

NETWORK PRUNING

10
24 Feb 2020

Picking Winning Tickets Before Training by Preserving Gradient Flow

ICLR 2020 alecwangcq/GraSP

Overparameterization has been shown to benefit both the optimization and generalization of neural networks, but large networks are resource hungry at both training and test time.

NETWORK PRUNING

43
18 Feb 2020

Filter Sketch for Network Pruning

23 Jan 2020lmbxmu/FilterSketch

Network pruning with information preserving can be approximated as a matrix sketch problem, which is efficiently solved by the off-the-shelf Frequent Direction method.

NETWORK PRUNING

28
23 Jan 2020

Quantisation and Pruning for Neural Network Compression and Regularisation

14 Jan 2020kpaupamah/compression-and-regularisation

Deep neural networks are typically too computationally expensive to run in real-time on consumer-grade hardware and low-powered devices.

NETWORK PRUNING NEURAL NETWORK COMPRESSION

5
14 Jan 2020