Article
Computer Science, Artificial Intelligence
Lai Wei, Fenfen Ji, Hao Liu, Rigui Zhou, Changming Zhu, Xiafen Zhang
Summary: This article revisited the data reconstruction problem in spectral clustering-based algorithms and proposed the concept of "relation reconstruction." By introducing the idea of neighborhood relation, a new method called sparse relation representation (SRR) was developed for subspace clustering, with a further extension known as structured sparse relation representation (SSRR) incorporating local structure information. The proposed optimization algorithm was analyzed for computational burden and convergence, with experiments demonstrating the superior performance of SRR and SSRR on various databases.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Hankui Peng, Nicos G. Pavlidis
Summary: In this paper, a novel spectral-based subspace clustering algorithm is proposed and extended to a constrained clustering and active learning framework. Extensive experiments show that the proposed approach is effective and competitive with state-of-the-art methods.
DATA MINING AND KNOWLEDGE DISCOVERY
(2022)
Article
Computer Science, Artificial Intelligence
Kajal Eybpoosh, Mansoor Rezghi, Abbas Heydari
Summary: This paper presents a method for clustering data points on submanifolds of an unknown manifold. The method maps the intrinsic manifolds to n-spheres using conformal mapping, preserving angles and sparse similarities. The proposed method improves the efficiency of sparse subspace clustering on special manifold data.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Wenyu Hu, Xuefang Zhu, Tinghua Wang, Yun Yi, Gaohang Yu
Summary: In this paper, a novel discrete subspace structure (DSS) constrained approach is proposed for recovering human mocap data by jointly optimizing the tasks of subspace clustering and low-rank matrix completion (LRMC). Experimental results validate the effectiveness of the proposed algorithm in both mocap data recovery and temporal subspace clustering.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Information Systems
Siyuan Zhao
Summary: Sparse subspace clustering is a widely used method for clustering high dimensional data. However, the traditional method is complex and requires prior information. In this paper, we propose a new method called Self-constrained Sparse Subspace Clustering (ScSSC) to simplify the clustering of high dimensional data. The proposed algorithm is a non-deep neural network model that can discover a high-quality cluster structure without prior information, making it highly effective in unsupervised scenarios.
Article
Computer Science, Artificial Intelligence
Libin Wang, Yulong Wang, Hao Deng, Hong Chen
Summary: This paper proposes a robust sparse subspace clustering method called ARSSC, which assigns small weights to corrupted entries in each data point, reducing the attention to them. Non-convex penalties are also utilized to overcome the overpenalized problem. The effectiveness of the proposed method is validated through experiments on real-world databases.
PATTERN RECOGNITION
(2023)
Article
Environmental Sciences
Jhon Lopez, Carlos Hinojosa, Henry Arguello
Summary: The unsupervised classification of hyperspectral images using sparse subspace clustering (SSC) faces limitations due to the number of spectral pixels, but this study proposes an efficient SSC-based method that reduces computational complexity through similarity-constrained sampling. Experimental results demonstrate that this method outperforms baseline methods with up to 30% higher accuracy and up to six times faster computing time.
JOURNAL OF APPLIED REMOTE SENSING
(2021)
Article
Automation & Control Systems
Feiping Nie, Wei Chang, Rong Wang, Xuelong Li
Summary: This article focuses on the utilization of co-clustering algorithms to solve the subspace clustering problem. Co-clustering methods, unlike traditional graph-based approaches, can extract the duality relationship between samples and features using bipartite graphs, leading to more information extraction. The proposed novel method combines dictionary learning with a bipartite graph under the constraint of the (normalized) Laplacian rank to address the subspace clustering problem. Experimental results demonstrate the effectiveness and stability of the model.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Computer Science, Information Systems
Bing Cai, Gui-Fu Lu
Summary: This study proposes a subspace clustering method for tensor data, which avoids damaging the inherent spatial structure of the data caused by the vectorization process. The method models the data using tensor nuclear norm and t-product, and explores the consensus information among the low-rank representation tensor to improve clustering performance.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Jianxi Zhao, Yang Li
Summary: This paper proposes a multi-view subspace clustering method called Hashing Multi-view Sparse Subspace Learning (HMSSL). HMSSL combines multi-view binary code learning and binary sparse subspace learning to address the issues of computational efficiency and effective subspace clustering structure exploration.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Yu Guo, Yuan Sun, Zheng Wang, Feiping Nie, Fei Wang
Summary: In this article, a novel unsupervised feature selection model, DSFEL, is proposed. DSFEL includes a module for learning a block-diagonal structural sparse graph to represent the clustering structure and another module for learning a completely row-sparse projection matrix using the l(2,0)-norm constraint to select distinctive features. Experimental results on nine real-world datasets demonstrate that the proposed method outperforms existing state-of-the-art unsupervised feature selection methods.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Jyoti Maggu, Angshul Majumdar
Summary: The conventional subspace clustering methods assume that the data can be separated into different subspaces, but what if this assumption doesn't hold? We propose a novel subspace clustering framework that can work even if the raw data is not separable into separate subspaces, and it also extends to non-linear manifolds.
Article
Engineering, Electrical & Electronic
Carlos Hinojosa, Esteban Vera, Henry Arguello
Summary: This article proposes a fast algorithm that obtains a sparse representation coefficient matrix by first selecting a small set of pixels that best represent their neighborhood. Then, it performs spatial filtering to enforce the connectivity of neighboring pixels and uses fast spectral clustering to get the final clustering map. Extensive simulations demonstrate the effectiveness of this method in unsupervised HSI classification.
IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING
(2021)
Article
Genetics & Heredity
Xiang-Zhen Kong, Yu Song, Jin-Xing Liu, Chun-Hou Zheng, Sha-Sha Yuan, Juan Wang, Ling-Yun Dai
Summary: The novel dimensionality reduction method PL21GPCA proposed in this article plays a crucial role in mining useful information from large-scale gene expression data. By applying different norm constraints, the method ensures robustness against outliers and noise, as well as enhances the sparsity of gene expression. Experimental results demonstrate the superior performance of the method in tumor sample clustering and gene network module discovery.
FRONTIERS IN GENETICS
(2021)
Article
Computer Science, Artificial Intelligence
Wenwen Min, Taosheng Xu, Xiang Wan, Tsung-Hui Chang
Summary: Non-negative matrix factorization (NMF) is a powerful tool for dimensionality reduction and clustering. This paper introduces a row-sparse NMF with l(2,0)-norm constraint (NMF_l(20)), which incorporates feature selection by constraining the basis matrix W using the l(2,0)-norm constraint. The problem of solving the model is addressed by proving that the l(2,0)-norm constraint satisfies the Kurdyka-Lojasiewicz property and proposing a proximal alternating linearized minimization algorithm and its accelerated version.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Operations Research & Management Science
Hao Jiang, Daniel P. Robinson, Rene Vidal, Chong You
COMPUTATIONAL OPTIMIZATION AND APPLICATIONS
(2018)
Article
Engineering, Electrical & Electronic
Chun-Guang Li, Chong You, Rene Vidal
IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING
(2018)
Article
Computer Science, Artificial Intelligence
Chong You, Chi Li, Daniel P. Robinson, Rene Vidal
Summary: This paper introduces a new exemplar selection model that chooses representative samples by reconstructing and covering the data points. By introducing a farthest first search algorithm, this method can efficiently select samples that meet the criteria. In addition, we also develop an efficient and robust subspace clustering method for imbalanced data.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Shangzhi Zhang, Chong You, Rene Vidal, Chun-Guang Li
Summary: In this paper, a novel subspace clustering framework SENet is proposed, which can learn self-expressive coefficients and handle out-of-sample data, as well as perform subspace clustering on large-scale datasets. Extensive experiments demonstrate the effectiveness of SENet on various benchmark datasets.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Mustafa D. Kaba, Chong You, Daniel P. Robinson, Enrique Mallada, Rene Vidal
Summary: This paper introduces a necessary and sufficient condition for subspace-preserving recovery, inspired by classical nullspace property. Through equivalent characterizations, the relationship between data distribution and recovery success is explained, and new sufficient conditions based on inner-radius and outer-radius measures are derived to provide a more comprehensive understanding in the field of subspace-preserving recovery. These results address an important gap in the existing literature.
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Ying Chen, Chun-Guang Li, Chong You
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Connor Lane, Ron Boger, Chong You, Manolis C. Tsakiris, Benjamin D. Haeffele, Rene Vidal
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Chong You, Chun-Guang Li, Daniel P. Robinson, Rene Vidal
2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Junjian Zhang, Chun-Guang Li, Chong You, Xianbiao Qi, Honggang Zhang, Jun Guo, Zhouchen Lin
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Article
Demography
Stephane Helleringer, Chong You, Laurence Fleury, Laetitia Douillot, Insa Diouf, Cheikh Tidiane Ndiaye, Valerie Delaunay, Rene Vidal
DEMOGRAPHIC RESEARCH
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Chong You, Daniel P. Robinson, Rene Vidal
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Proceedings Paper
Computer Science, Information Systems
Chong You, Claire Donnat, Daniel P. Robinson, Rene Vidal
2016 50TH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS AND COMPUTERS
(2016)