Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userShapley Value as Principled Metric for Structured Network Pruning
292
0
0.0
(
0
)
Added by
Marco Ancona
Publication date
2020
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Structured pruning is a well-known technique to reduce the storage size and inference cost of neural networks. The usual pruning pipeline consists of ranking the network internal filters and activations with respect to their contributions to the network performance, removing the units with the lowest contribution, and fine-tuning the network to reduce the harm induced by pruning. Recent results showed that random pruning performs on par with other metrics, given enough fine-tuning resources. In this work, we show that this is not true on a low-data regime when fine-tuning is either not possible or not effective. In this case, reducing the harm caused by pruning becomes crucial to retain the performance of the network. First, we analyze the problem of estimating the contribution of hidden units with tools suggested by cooperative game theory and propose Shapley values as a principled ranking metric for this task. We compare with several alternatives proposed in the literature and discuss how Shapley values are theoretically preferable. Finally, we compare all ranking metrics on the challenging scenario of low-data pruning, where we demonstrate how Shapley values outperform other heuristics.
rate research
Read More
In this paper, we propose a novel progressive parameter pruning method for Convolutional Neural Network acceleration, named Structured Probabilistic Pruning (SPP), which effectively prunes weights of convolutional layers in a probabilistic manner. Unlike existing deterministic pruning approaches, where unimportant weights are permanently eliminated, SPP introduces a pruning probability for each weight, and pruning is guided by sampling from the pruning probabilities. A mechanism is designed to increase and decrease pruning probabilities based on importance criteria in the training process. Experiments show that, with 4x speedup, SPP can accelerate AlexNet with only 0.3% loss of top-5 accuracy and VGG-16 with 0.8% loss of top-5 accuracy in ImageNet classification. Moreover, SPP can be directly applied to accelerate multi-branch CNN networks, such as ResNet, without specific adaptations. Our 2x speedup ResNet-50 only suffers 0.8% loss of top-5 accuracy on ImageNet. We further show the effectiveness of SPP on transfer learning tasks.
Structural pruning of neural network parameters reduces computation, energy, and memory transfer costs during inference. We propose a novel method that estimates the contribution of a neuron (filter) to the final loss and iteratively removes those with smaller scores. We describe two variations of our method using the first and second-order Taylor expansions to approximate a filters contribution. Both methods scale consistently across any network layer without requiring per-layer sensitivity analysis and can be applied to any kind of layer, including skip connections. For modern networks trained on ImageNet, we measured experimentally a high (>93%) correlation between the contribution computed by our methods and a reliable estimate of the true importance. Pruning with the proposed methods leads to an improvement over state-of-the-art in terms of accuracy, FLOPs, and parameter reduction. On ResNet-101, we achieve a 40% FLOPS reduction by removing 30% of the parameters, with a loss of 0.02% in the top-1 accuracy on ImageNet. Code is available at https://github.com/NVlabs/Taylor_pruning.
Deep Neural Networks (DNNs) are the key to the state-of-the-art machine vision, sensor fusion and audio/video signal processing. Unfortunately, their computation complexity and tight resource constraints on the Edge make them hard to leverage on mobile, embedded and IoT devices. Due to great diversity of Edge devices, DNN designers have to take into account the hardware platform and application requirements during network training. In this work we introduce pruning via matrix pivoting as a way to improve network pruning by compromising between the design flexibility of architecture-oblivious and performance efficiency of architecture-aware pruning, the two dominant techniques for obtaining resource-efficient DNNs. We also describe local and global network optimization techniques for efficient implementation of the resulting pruned networks. In combination, the proposed pruning and implementation result in close to linear speed up with the reduction of network coefficients during pruning.
Compressing Deep Neural Network (DNN) models to alleviate the storage and computation requirements is essential for practical applications, especially for resource limited devices. Although capable of reducing a reasonable amount of model parameters, previous unstructured or structured weight pruning methods can hardly truly accelerate inference, either due to the poor hardware compatibility of the unstructured sparsity or due to the low sparse rate of the structurally pruned network. Aiming at reducing both storage and computation, as well as preserving the original task performance, we propose a generalized weight unification framework at a hardware compatible micro-structured level to achieve high amount of compression and acceleration. Weight coefficients of a selected micro-structured block are unified to reduce the storage and computation of the block without changing the neuron connections, which turns to a micro-structured pruning special case when all unified coefficients are set to zero, where neuron connections (hence storage and computation) are completely removed. In addition, we developed an effective training framework based on the alternating direction method of multipliers (ADMM), which converts our complex constrained optimization into separately solvable subproblems. Through iteratively optimizing the subproblems, the desired micro-structure can be ensured with high compression ratio and low performance degradation. We extensively evaluated our method using a variety of benchmark models and datasets for different applications. Experimental results demonstrate state-of-the-art performance.
Convolutional neural networks (CNNs) have proven to be highly successful at a range of image-to-image tasks. CNNs can be computationally expensive, which can limit their applicability in practice. Model pruning can improve computational efficiency by sparsifying trained networks. Common methods for pruning CNNs determine what convolutional filters to remove by ranking filters on an individual basis. However, filters are not independent, as CNNs consist of chains of convolutions, which can result in sub-optimal filter selection. We propose a novel pruning method, LongEst-chAiN (LEAN) pruning, which takes the interdependency between the convolution operations into account. We propose to prune CNNs by using graph-based algorithms to select relevant chains of convolutions. A CNN is interpreted as a graph, with the operator norm of each convolution as distance metric for the edges. LEAN pruning iteratively extracts the highest value path from the graph to keep. In our experiments, we test LEAN pruning for several image-to-image tasks, including the well-known CamVid dataset. LEAN pruning enables us to keep just 0.5%-2% of the convolutions without significant loss of accuracy. When pruning CNNs with LEAN, we achieve a higher accuracy than pruning filters individually, and different pruned substructures emerge.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
