Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders

• URL: http://arxiv.org/abs/2012.00560v1
• Date: Tue, 1 Dec 2020 15:05:15 GMT
• Title: Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders
• Authors: Zahra Atashgahi, Ghada Sokar, Tim van der Lee, Elena Mocanu, Decebal Constantin Mocanu, Raymond Veldhuis, Mykola Pechenizkiy
• Abstract summary: Feature selection, which identifies the most relevant and informative attributes of a dataset, has been introduced as a solution to this problem. Most of the existing feature selection methods are computationally inefficient. In this paper, a novel and flexible method for unsupervised feature selection is proposed.
• Score: 4.561081324313315
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Major complications arise from the recent increase in the amount of high-dimensional data, including high computational costs and memory requirements. Feature selection, which identifies the most relevant and informative attributes of a dataset, has been introduced as a solution to this problem. Most of the existing feature selection methods are computationally inefficient; inefficient algorithms lead to high energy consumption, which is not desirable for devices with limited computational and energy resources. In this paper, a novel and flexible method for unsupervised feature selection is proposed. This method, named QuickSelection, introduces the strength of the neuron in sparse neural networks as a criterion to measure the feature importance. This criterion, blended with sparsely connected denoising autoencoders trained with the sparse evolutionary training procedure, derives the importance of all input features simultaneously. We implement QuickSelection in a purely sparse manner as opposed to the typical approach of using a binary mask over connections to simulate sparsity. It results in a considerable speed increase and memory reduction. When tested on several benchmark datasets, including five low-dimensional and three high-dimensional datasets, the proposed method is able to achieve the best trade-off of classification and clustering accuracy, running time, and maximum memory usage, among widely used approaches for feature selection. Besides, our proposed method requires the least amount of energy among the state-of-the-art autoencoder-based feature selection methods.

Related papers

• Large-scale Multi-objective Feature Selection: A Multi-phase Search Space Shrinking Approach [0.27624021966289597]
  Feature selection is a crucial step in machine learning, especially for high-dimensional datasets. This paper proposes a novel large-scale multi-objective evolutionary algorithm based on the search space shrinking, termed LMSSS. The effectiveness of the proposed algorithm is demonstrated through comprehensive experiments on 15 large-scale datasets.
  arXiv  Detail & Related papers  (2024-10-13T23:06:10Z)
• Center-Sensitive Kernel Optimization for Efficient On-Device Incremental Learning [88.78080749909665]
  Current on-device training methods just focus on efficient training without considering the catastrophic forgetting. This paper proposes a simple but effective edge-friendly incremental learning framework. Our method achieves average accuracy boost of 38.08% with even less memory and approximate computation.
  arXiv  Detail & Related papers  (2024-06-13T05:49:29Z)
• Switchable Decision: Dynamic Neural Generation Networks [98.61113699324429]
  We propose a switchable decision to accelerate inference by dynamically assigning resources for each data instance. Our method benefits from less cost during inference while keeping the same accuracy.
  arXiv  Detail & Related papers  (2024-05-07T17:44:54Z)
• A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning [131.2910403490434]
  Data scientists typically collect as many features as possible into their datasets, and even engineer new features from existing ones. Existing benchmarks for tabular feature selection consider classical downstream models, toy synthetic datasets, or do not evaluate feature selectors on the basis of downstream performance. We construct a challenging feature selection benchmark evaluated on downstream neural networks including transformers. We also propose an input-gradient-based analogue of Lasso for neural networks that outperforms classical feature selection methods on challenging problems.
  arXiv  Detail & Related papers  (2023-11-10T05:26:10Z)
• Heterogenous Memory Augmented Neural Networks [84.29338268789684]
  We introduce a novel heterogeneous memory augmentation approach for neural networks. By introducing learnable memory tokens with attention mechanism, we can effectively boost performance without huge computational overhead. We show our approach on various image and graph-based tasks under both in-distribution (ID) and out-of-distribution (OOD) conditions.
  arXiv  Detail & Related papers  (2023-10-17T01:05:28Z)
• Feature selection algorithm based on incremental mutual information and cockroach swarm optimization [12.297966427336124]
  We propose an incremental mutual information based improved swarm intelligent optimization method (IMIICSO) This method extracts decision table reduction knowledge to guide group algorithm global search. The accuracy of feature subsets selected by the improved cockroach swarm algorithm based on incremental mutual information is better or almost the same as that of the original swarm intelligent optimization algorithm.
  arXiv  Detail & Related papers  (2023-02-21T08:51:05Z)
• Variable Bitrate Neural Fields [75.24672452527795]
  We present a dictionary method for compressing feature grids, reducing their memory consumption by up to 100x. We formulate the dictionary optimization as a vector-quantized auto-decoder problem which lets us learn end-to-end discrete neural representations in a space where no direct supervision is available.
  arXiv  Detail & Related papers  (2022-06-15T17:58:34Z)
• Compactness Score: A Fast Filter Method for Unsupervised Feature Selection [66.84571085643928]
  We propose a fast unsupervised feature selection method, named as, Compactness Score (CSUFS) to select desired features. Our proposed algorithm seems to be more accurate and efficient compared with existing algorithms.
  arXiv  Detail & Related papers  (2022-01-31T13:01:37Z)
• A concise method for feature selection via normalized frequencies [0.0]
  In this paper, a concise method is proposed for universal feature selection. The proposed method uses a fusion of the filter method and the wrapper method, rather than a combination of them. The evaluation results show that the proposed method outperformed several state-of-the-art related works in terms of accuracy, precision, recall, F-score and AUC.
  arXiv  Detail & Related papers  (2021-06-10T15:29:54Z)
• Feature Selection Using Batch-Wise Attenuation and Feature Mask Normalization [6.6357750579293935]
  This paper proposes a feature mask module (FM- module) for feature selection based on a novel batch-wise attenuation and feature mask normalization. Experiments on popular image, text and speech datasets have shown that our approach is easy to use and has superior performance in comparison with other state-of-the-art deep-learning-based feature selection methods.
  arXiv  Detail & Related papers  (2020-10-26T14:46:38Z)
• Review of Swarm Intelligence-based Feature Selection Methods [3.8848561367220276]
  Data mining applications with high dimensional datasets require high speed and accuracy. One of the dimensionality reduction approaches is feature selection that can increase the accuracy of the data mining task. State-of-the-art swarm intelligence are studied, and the recent feature selection methods based on these algorithms are reviewed.
  arXiv  Detail & Related papers  (2020-08-07T05:18:58Z)

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.