Efficient and Robust Feature Selection via Joint ℓ2, 1-Norms Minimization

By Feiping Nie, Heng Huang, Xiao Cai, Chris H. Q. Ding. 2010

2,014 citations recorded by the source corpus.

How researchers see this paper

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

1. Dacheng Tao
2. Feiping Nie
3. Yi Yang
4. Mingsheng Long
5. Xuelong Li
6. Qiang Yang
7. Yu Zhang
8. Luc Van Gool

Citations in the corpus

• Joint Embedding Learning and Sparse Regression: A Framework for Unsupervised Feature Selection (2014, methodology): “Inspired by [40], we will solve this problem in an alternative way.”
• Multi-View Clustering and Semi-Supervised Classification with Adaptive Neighbours (2017, methodology): “The proposed algorithm can find a local optimal solution, to prove its convergence, we need to utilize the lemma introduce by (Nie et al. 2010) Lemma 1 For any positive real number u and v, the following inequality holds: √ u− u 2 √ v ≤ √v − v 2 √ v .”
• Semi-supervised Robust Dictionary Learning via Efficient l-Norms Minimization (2013, methodology): “∙ We address the dictionary robustness problem by using a new l2,0+ -norm loss function, which is a generalization of traditional l2,1-norm loss function [11, 4], yet more robust against noisy and outlier training samples.”
• Supervised, Unsupervised, and Semi-Supervised Feature Selection: A Review on Gene Selection (2016, methodology): “Thus, the development or ; [63]; [70]; [51]; [77]; [78]; [79]; [81]; [82]; [83]; [84]; [87]; [89]; [88]; [12]; [90]; [137]; [124]; [129]; [139]; [127]; [128]; [49]; [147]; [146]; Wrapper [91]; [92]; [93]; [94]; [96]; [52]; [98]; [100]; [99]; [132];[131]; [151]; [154]; Embedded [53]; [103]; [104]; [5”
• Deep Feature Selection: Theory and Application to Identify Enhancers and Promoters (2015, unknown): “This is because b k (cid:2) W k 1 = b P i P j j w i w ij j in Equation (8) and Therefore, we cannot find a value of b to guarantee b k (cid:2) W Inspired by works of non-negative matrix factorization (NMF) (Nie et al., 2010; Kong et al., 2011), we learn that the row-wise sparseness of a matrix can be”
• Radar: Residual Analysis for Anomaly Detection in Attributed Networks (2017, unknown): “:) are non-zero vectors [Nie et al., 2010]: ||Wt+1||2,1 − ∑ i ||Wt+1(i, :)||22 2||Wt(i, :)||2 ≤||Wt||2,1 − ∑ i ||Wt(i, :)||22 2||Wt(i, :)||2 , (12) where Wt denotes the update of W at the t-th iteration.”
• Feature Selection (2016, methodology): “The trace ratio criterion (Nie et al. 2008) directly selects the global optimal feature subset based on the corresponding score, which is computed by a trace ratio norm.”
• Semantically Tied Paired Cycle Consistency for Zero-Shot Sketch-Based Image Retrieval (2019, unknown): “‖2,1 indicates `2,1 norm [43].”
• Robust Matrix Completion via Joint Schatten p-Norm and lp-Norm Minimization (2012, methodology): “We also use the lp-norm (0 < p ≤ 1) as the error function to improve the robustness to outliers in given data [14], and propose to solve the following robust matrix completion problem (we”
• An Adaptive Semisupervised Feature Analysis for Video Semantic Recognition (2018, background): “Note that all feature (All-Fea), sparse multinomial logistic regression via Bayesian 1 regularization (SBMLR), and feature selection via joint 2,1-norm minimization (FSNM) are designed for supervised feature selection.”
• Capped Lp-Norm Graph Embedding for Photo Clustering (2016, methodology): “This model learns an efficient graph embedding by utilizing capped (cid:96) p -norm to remove data outliers.”
• Active Lifelong Learning With "Watchdog" (2018, unknown): “(14) A simple idea is to set the derivative of A as 0, and adopting the property that ΘTt Θt = Ik, we have: λ1(Θ T t ΘtA−ΘTt Dt+1) + λ2ΣA = 0, (15) where Σ is a diagonal matrix (Nie et al. 2010) of At with Σii = 1 2‖ai‖2 , i = 1, . . . , k.”
• Reconstruction-based Unsupervised Feature Selection: An Embedded Approach (2017, background): “…take advantage of the discriminative information encoded in class labels to select the subset of features that are able to distinguish instances from different classes [Tibshirani, 1996; Ding and Peng, 2005; Nie et al., 2008; 2010; Cover and Thomas, 2012; Jian et al., 2016; Li et al., 2017].”