Robust Joint Graph Sparse Coding for Unsupervised Spectral Feature Selection

By Xiaofeng Zhu, Xuelong Li, Shichao Zhang, Chun-hua Ju, Xindong Wu. 2017

318 citations recorded by the source corpus.

In this paper, we propose a new unsupervised spectral feature selection model by embedding a graph regularizer into the framework of joint sparse regression for preserving the local structures of data. To do this, we first extract the bases of training data by previous dictionary learning methods and, then, map original data into the basis space to generate their new representations, by proposing a novel joint graph sparse coding (JGSC) model. In JGSC, we first formulate its objective function by simultaneously taking subspace learning and joint sparse regression into account, then, design a new optimization solution to solve the resulting objective function, and further prove the convergence of the proposed solution. Furthermore, we extend JGSC to a robust JGSC (RJGSC) via replacing the least square loss function with a robust loss function, for achieving the same goals and also avoiding the impact of outliers. Finally, experimental results on real data sets showed that both JGSC and RJGSC outperformed the state-of-the-art algorithms in terms of ${k}$ -nearest neighbor classification performance.

Subfields: Artificial Intelligence, Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Qiang Yang
2. Yu Zhang
3. Ming Zong
4. Debo Cheng
5. Xuelong Li
6. Shichao Zhang
7. Jian Weng
8. Xuelian Deng

In Computational Mechanics

1. Qiang Yang
2. Yu Zhang
3. Xiaofeng Zhu
4. Shichao Zhang
5. Xuelong Li

In Computer Vision and Pattern Recognition

1. Qiang Yang
2. Yu Zhang
3. Ming Zong
4. Shichao Zhang
5. Debo Cheng
6. Xuelong Li
7. Xiaofeng Zhu
8. Jian Weng

Citations in the corpus

• A Survey on Multi-Task Learning (2017, methodology): “In [138], a multi-task spectral clustering algorithm, which can handle the out-of-sample issue via a linear function to learn the cluster assignment, is proposed to achieve the feature selection among tasks via the ‘2;1 regularization [139].”
• Learning k for kNN Classification (2017, methodology): “(3) The (cid:2) 1 -norm has been proved to lead the optimal sparse W ∗ [Zhu et al. 2016a; Wang et al. 2014; Zhang et al. 2011].”
• Pattern Recognition (2018, unknown): “In this setting, viewpoint changes can be alleviated since we can find any corresponding angle for a probe.”
• Feature selection for text classification: A review (2018, methodology): “…similarity preserving feature selection [112], feature selection with optimization techniques [105], regularization based feature selection methods [121], feature selection with machine learning techniques [25, 38, 39, 53, 115, 119, 123], stability measures for feature selection algorithms [46].”