mlsanityData to 7 Oct 2026

Supervised Feature Selection with Neuron Evolution in Sparse Neural Networks

arXiv 2303.07200 ↗First posted 10 Mar 2023cs.NE cs.AI cs.LGcited by 7

Not on the map. Why?

Abstract (arXiv)

Feature selection that selects an informative subset of variables from data not only enhances the model interpretability and performance but also alleviates the resource demands. Recently, there has been growing attention on feature selection using neural networks. However, existing methods usually suffer from high computational costs when applied to high-dimensional datasets. In this paper, inspired by evolution processes, we propose a novel resource-efficient supervised feature selection method using sparse neural networks, named enquoteNeuroFS. 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. By performing several experiments on 11 low and high-dimensional real-world benchmarks of different types, we demonstrate that NeuroFS achieves the highest ranking-based score among the considered state-of-the-art supervised feature selection models. The code is available on GitHub.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 30 of its 61 references that are in the map. First posted on arXiv 10 Mar 2023.

Builds on

30 of 61 references.

References · 30

  1. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  2. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 1,998
  3. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 802
  4. 2017Deep Learning Scaling is Predictable, Empiricallycited by 556
  5. 2019Importance Estimation for Neural Network Pruningcited by 531
  6. 2021Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networkscited by 521
  7. 2019Rigging the Lottery: Making All Tickets Winnerscited by 491
  8. 2019The State of Sparsity in Deep Neural Networkscited by 471
  9. 2017Scalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Sciencecited by 325
  10. 2019Sparse Networks from Scratch: Faster Training without Losing Performancecited by 210
  11. 2019Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterizationcited by 187
  12. 2020The Hardware Lotterycited by 160
18 more
  1. 2017Deep Rewiring: Training very sparse deep networkscited by 136
  2. 2021Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Trainingcited by 107
  3. 2019Concrete Autoencoders for Differentiable Feature Selection and Reconstructioncited by 90
  4. 2021Sparse Training via Boosting Pruning Plasticity with Neuroregenerationcited by 83
  5. 2019LassoNet: A Neural Network with Feature Sparsitycited by 81
  6. 2021Top-KAST: Top-K Always Sparse Trainingcited by 79
  7. 2020Gradient Flow in Sparse Neural Networks and How Lottery Tickets Wincited by 77
  8. 2017NeST: A Neural Network Synthesis Tool Based on a Grow-and-Prune Paradigmcited by 60
  9. 2021Dynamic Sparse Training for Deep Reinforcement Learningcited by 49
  10. 2018DeepPINK: reproducible feature selection in deep neural networkscited by 41
  11. 2016A topological insight into restricted Boltzmann machinescited by 32
  12. 2020Feature Importance Ranking for Deep Learningcited by 31
  13. 2020Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoderscited by 27
  14. 2020FsNet: Feature Selection Network on High-dimensional Biological Datacited by 23
  15. 2020Topological Insights into Sparse Neural Networkscited by 21
  16. 2021Sparse Training Theory for Scalable and Efficient Agentscited by 12
  17. 2021Deep Unsupervised Feature Selection by Discarding Nuisance and Correlated Featurescited by 11
  18. 2019A Brain-inspired Algorithm for Training Highly Sparse Neural Networkscited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 3; 2025: 1; 2026: 1.

7 papers.

  1. 2024Unveiling the Power of Sparse Neural Networks for Feature Selectioncited by 3
  2. 2023Effective Neural Network L0 Regularization With BinMaskcited by 2
  3. 2025Embedded Federated Feature Selection with Dynamic Sparse Training: Balancing Accuracy-Cost Tradeoffscited by 1
  4. 2023Feature selection simultaneously preserving both class and cluster structurescited by 0
  5. 2024C-XGBoost: A tree boosting model for causal effect estimationcited by 0
  6. 2024EntryPrune: Neural Network Feature Selection using First Impressionscited by 0
  7. 2026Sparse Bayesian Deep Functional Learning with Structured Region Selectioncited by 0