Unveiling the Power of Sparse Neural Networks for Feature Selection
- URL: http://arxiv.org/abs/2408.04583v1
- Date: Thu, 8 Aug 2024 16:48:33 GMT
- Title: Unveiling the Power of Sparse Neural Networks for Feature Selection
- Authors: Zahra Atashgahi, Tennison Liu, Mykola Pechenizkiy, Raymond Veldhuis, Decebal Constantin Mocanu, Mihaela van der Schaar,
- Abstract summary: Sparse Neural Networks (SNNs) have emerged as powerful tools for efficient feature selection.
We show that SNNs trained with dynamic sparse training (DST) algorithms can achieve, on average, more than $50%$ memory and $55%$ FLOPs reduction.
Our findings show that feature selection with SNNs trained with DST algorithms can achieve, on average, more than $50%$ memory and $55%$ FLOPs reduction.
- Score: 60.50319755984697
- License: http://creativecommons.org/licenses/by-sa/4.0/
- Abstract: Sparse Neural Networks (SNNs) have emerged as powerful tools for efficient feature selection. Leveraging the dynamic sparse training (DST) algorithms within SNNs has demonstrated promising feature selection capabilities while drastically reducing computational overheads. Despite these advancements, several critical aspects remain insufficiently explored for feature selection. Questions persist regarding the choice of the DST algorithm for network training, the choice of metric for ranking features/neurons, and the comparative performance of these methods across diverse datasets when compared to dense networks. This paper addresses these gaps by presenting a comprehensive systematic analysis of feature selection with sparse neural networks. Moreover, we introduce a novel metric considering sparse neural network characteristics, which is designed to quantify feature importance within the context of SNNs. Our findings show that feature selection with SNNs trained with DST algorithms can achieve, on average, more than $50\%$ memory and $55\%$ FLOPs reduction compared to the dense networks, while outperforming them in terms of the quality of the selected features. Our code and the supplementary material are available on GitHub (\url{https://github.com/zahraatashgahi/Neuron-Attribution}).
Related papers
- RelChaNet: Neural Network Feature Selection using Relative Change Scores [0.0]
We introduce RelChaNet, a novel and lightweight feature selection algorithm that uses neuron pruning and regrowth in the input layer of a dense neural network.
Our approach generally outperforms the current state-of-the-art methods, and in particular improves the average accuracy by 2% on the MNIST dataset.
arXiv Detail & Related papers (2024-10-03T09:56:39Z) - A Hybrid Neural Coding Approach for Pattern Recognition with Spiking
Neural Networks [53.31941519245432]
Brain-inspired spiking neural networks (SNNs) have demonstrated promising capabilities in solving pattern recognition tasks.
These SNNs are grounded on homogeneous neurons that utilize a uniform neural coding for information representation.
In this study, we argue that SNN architectures should be holistically designed to incorporate heterogeneous coding schemes.
arXiv Detail & Related papers (2023-05-26T02:52:12Z) - Supervised Feature Selection with Neuron Evolution in Sparse Neural
Networks [17.12834153477201]
We propose a novel resource-efficient supervised feature selection method using sparse neural networks.
By gradually pruning the uninformative features from the input layer of a sparse neural network trained from scratch, NeuroFS derives an informative subset of features efficiently.
NeuroFS achieves the highest ranking-based score among the considered state-of-the-art supervised feature selection models.
arXiv Detail & Related papers (2023-03-10T17:09:55Z) - Random Features for the Neural Tangent Kernel [57.132634274795066]
We propose an efficient feature map construction of the Neural Tangent Kernel (NTK) of fully-connected ReLU network.
We show that dimension of the resulting features is much smaller than other baseline feature map constructions to achieve comparable error bounds both in theory and practice.
arXiv Detail & Related papers (2021-04-03T09:08:12Z) - Feature Selection Based on Sparse Neural Network Layer with Normalizing
Constraints [0.0]
We propose new neural-network based feature selection approach that introduces two constrains, the satisfying of which leads to sparse FS layer.
The results confirm that proposed Feature Selection Based on Sparse Neural Network Layer with Normalizing Constraints (SNEL-FS) is able to select the important features and yields superior performance compared to other conventional FS methods.
arXiv Detail & Related papers (2020-12-11T14:14:33Z) - Encoding the latent posterior of Bayesian Neural Networks for
uncertainty quantification [10.727102755903616]
We aim for efficient deep BNNs amenable to complex computer vision architectures.
We achieve this by leveraging variational autoencoders (VAEs) to learn the interaction and the latent distribution of the parameters at each network layer.
Our approach, Latent-Posterior BNN (LP-BNN), is compatible with the recent BatchEnsemble method, leading to highly efficient (in terms of computation and memory during both training and testing) ensembles.
arXiv Detail & Related papers (2020-12-04T19:50:09Z) - Progressive Tandem Learning for Pattern Recognition with Deep Spiking
Neural Networks [80.15411508088522]
Spiking neural networks (SNNs) have shown advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency.
We propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern recognition.
arXiv Detail & Related papers (2020-07-02T15:38:44Z) - Convolutional Spiking Neural Networks for Spatio-Temporal Feature
Extraction [3.9898522485253256]
Spiking neural networks (SNNs) can be used in low-power and embedded systems.
temporal coding in layers of convolutional neural networks and other types of SNNs has yet to be studied.
We present a new deep spiking architecture to tackle real-world problems.
arXiv Detail & Related papers (2020-03-27T11:58:51Z) - Rectified Linear Postsynaptic Potential Function for Backpropagation in
Deep Spiking Neural Networks [55.0627904986664]
Spiking Neural Networks (SNNs) usetemporal spike patterns to represent and transmit information, which is not only biologically realistic but also suitable for ultra-low-power event-driven neuromorphic implementation.
This paper investigates the contribution of spike timing dynamics to information encoding, synaptic plasticity and decision making, providing a new perspective to design of future DeepSNNs and neuromorphic hardware systems.
arXiv Detail & Related papers (2020-03-26T11:13:07Z) - Widening and Squeezing: Towards Accurate and Efficient QNNs [125.172220129257]
Quantization neural networks (QNNs) are very attractive to the industry because their extremely cheap calculation and storage overhead, but their performance is still worse than that of networks with full-precision parameters.
Most of existing methods aim to enhance performance of QNNs especially binary neural networks by exploiting more effective training techniques.
We address this problem by projecting features in original full-precision networks to high-dimensional quantization features.
arXiv Detail & Related papers (2020-02-03T04:11:13Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.