Pruner in NNI¶
NNI implements the main part of the pruning algorithm as pruner. All pruners are implemented as close as possible to what is described in the paper (if it has). The following table provides a brief introduction to the pruners implemented in nni, click the link in table to view a more detailed introduction and use cases.
There are two kinds of pruners in NNI, please refer to basic pruner and scheduled pruner for details.
Name 
Brief Introduction of Algorithm 

Pruning the specified ratio on each weight element based on absolute value of weight element 

Pruning output channels with the smallest L1 norm of weights (Pruning Filters for Efficient Convnets) Reference Paper 

Pruning output channels with the smallest L2 norm of weights 

Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration Reference Paper 

Pruning output channels by pruning scaling factors in BN layers(Learning Efficient Convolutional Networks through Network Slimming) Reference Paper 

Pruning output channels based on the metric APoZ (average percentage of zeros) which measures the percentage of zeros in activations of (convolutional) layers. Reference Paper 

Pruning output channels based on the metric that calculates the smallest mean value of output activations 

Pruning filters based on the first order taylor expansion on weights(Importance Estimation for Neural Network Pruning) Reference Paper 

Pruning based on ADMM optimization technique Reference Paper 

Sparsity ratio increases linearly during each pruning rounds, in each round, using a basic pruner to prune the model. 

Automated gradual pruning (To prune, or not to prune: exploring the efficacy of pruning for model compression) Reference Paper 

The pruning process used by “The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks”. It prunes a model iteratively. Reference Paper 

Automatic pruning with a guided heuristic search method, Simulated Annealing algorithm Reference Paper 

Automatic pruning by iteratively call SimulatedAnnealing Pruner and ADMM Pruner Reference Paper 

AMC: AutoML for Model Compression and Acceleration on Mobile Devices Reference Paper 

Movement Pruning: Adaptive Sparsity by FineTuning Reference Paper 