# Low-Dimensional Representation-Driven TSK Fuzzy System for Feature Selection

arXiv: https://arxiv.org/abs/2501.12607 · HTML: https://mlsanity.com/paper/2501.12607/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 48 references that are in the map.
- First posted on arXiv 22 Jan 2025.

## Builds on (most cited first, 6 of 6)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [DAGs with NO TEARS: Continuous Optimization for Structure Learning](https://mlsanity.com/paper/1803.01422/) (2018)
- [Hamiltonian Variational Auto-Encoder](https://mlsanity.com/paper/1805.11328/) (2018)
- [Supervised feature selection with orthogonal regression and feature weighting](https://mlsanity.com/paper/1910.03787/) (2019)
- [On the Functional Equivalence of TSK Fuzzy Systems to Neural Networks, Mixture of Experts, CART, and Stacking Ensemble Regression](https://mlsanity.com/paper/1903.10572/) (2019)

## Abstract (arXiv)

Feature selection can select important features to address dimensional curses. Subspace learning, a widely used dimensionality reduction method, can project the original data into a low-dimensional space. However, the low-dimensional representation is often transformed back into the original space, resulting in information loss. Additionally, gate function-based methods in Takagi-Sugeno-Kang fuzzy system (TSK-FS) are commonly less discrimination. To address these issues, this paper proposes a novel feature selection method that integrates subspace learning with TSK-FS. Specifically, a projection matrix is used to fit the intrinsic low-dimensional representation. Subsequently, the low-dimensional representation is fed to TSK-FS to measure its availability. The firing strength is slacked so that TSK-FS is not limited by numerical underflow. Finally, the ℓ 2,1-norm is introduced to select significant features and the connection to related works is discussed. The proposed method is evaluated against six state-of-the-art methods on eighteen datasets, and the results demonstrate the superiority of the proposed method.