Efficient kNN Algorithm Based on Graph Sparse Reconstruction

Zhang, Shichao; Zong, Ming; Sun, Ke; Liu, Yue; Cheng, Debo

doi:10.1007/978-3-319-14717-8_28

Cited by 26 publications

(26 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our experiments, we selected state-of-the-art methods, including the standard kNN method, the kNN with cross-validation determined parameter k (we briefly denote it as CV-kNN), the L-kNN method [Zhang et al 2014] (compared to CM-kNN, it doesn't consider the importance of removing the noisy data points), the LL-kNN method (compared to CM-kNN, it doesn't consider the importance of preserving the local consistency of the structures of the data), the kNN-based Applicability Domain approach (AD-kNN) [Sahigara et al 2014], and the Large Margin Nearest Neighbor approach (LMNN) [Weinberger and Saul 2006].…”

Section: Competing Methodsmentioning

confidence: 99%

“…, 10, and the square root of the sample size. -The L-kNN method [Zhang et al 2014, that is, Equation (6) with the setting ρ 2 = 0, on which we would like to show the importance of removing the noisy data points. -The LL-kNN method, that is, Equation (6) with the setting ρ 3 = 0, on which we would like to show the importance of preserving the local consistency of the structures of the data.…”

Section: Competing Methodsmentioning

confidence: 99%

“…This article proposes a new kNN method by extending our conference version in Zhang et al [2014] 1 to address the above issue. This proposed method, referred to as the Correlation Matrix kNN (CM-kNN for short), is devised to learn different k values for different test data points by following the distribution of training data.…”

Section: Introductionmentioning

confidence: 99%

“…Compared to our conference version inZhang et al [2014], we have improved the abstract and introduction, added the newly literatures to the related work, rearranged the GS-kNN method[Zhang et al 2014], and added three comparison methods and 12 real datasets to the experimental part to examine the robustness and scalability of the proposed approach.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Learning k for kNN Classification

Zhang

Zong

et al. 2017

ACM Trans. Intell. Syst. Technol.

Self Cite

392

148

View full text Add to dashboard Cite

The K Nearest Neighbor (kNN) method has widely been used in the applications of data mining and machine learning due to its simple implementation and distinguished performance. However, setting all test data with the same k value in the previous kNN methods has been proven to make these methods impractical in real applications. This article proposes to learn a correlation matrix to reconstruct test data points by training data to assign different k values to different test data points, referred to as the Correlation Matrix kNN (CM-kNN for short) classification. Specifically, the least-squares loss function is employed to minimize the reconstruction error to reconstruct each test data point by all training data points. Then, a graph Laplacian regularizer is advocated to preserve the local structure of the data in the reconstruction process. Moreover, an 1-norm regularizer and an 2,1-norm regularizer are applied to learn different k values for different test data and to result in low sparsity to remove the redundant/noisy feature from the reconstruction process, respectively. Besides for classification tasks, the kNN methods (including our proposed CM-kNN method) are further utilized to regression and missing data imputation. We conducted sets of experiments for illustrating the efficiency, and experimental results showed that the proposed method was more accurate and efficient than existing kNN methods in data-mining applications, such as classification, regression, and missing data imputation.

show abstract

Section: Competing Methodsmentioning

confidence: 99%

Section: Competing Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Learning k for kNN Classification

Zhang

Zong

et al. 2017

ACM Trans. Intell. Syst. Technol.

Self Cite

392

148

View full text Add to dashboard Cite

show abstract

“…To develop Lasso-based SR classification systems, group lasso (GL) [17] [18], which uses the ' 2 -norm within a group and the ' 1 -norm between groups, has been applied to obtain sparse coefficients [19][20][21][22][23]. In [19], a localityconstrained GL coding method is used for microvessel image classification and realizes the automatic ''hot spot'' detection of angiogenesis for human liver carcinoma.…”

Section: Introductionmentioning

confidence: 99%

Exclusive lasso-based k-nearest-neighbor classification

Qiu

Shang

et al. 2021

Neural Comput & Applic

View full text Add to dashboard Cite

Conventionally, the k nearest-neighbor (kNN) classification is implemented with the use of the Euclidean distance-based measures, which are mainly the one-to-one similarity relationships such as to lose the connections between different samples. As a strategy to alleviate this issue, the coefficients coded by sparse representation have played a role of similarity gauger for nearest-neighbor classification as well. Although SR coefficients enjoy remarkable discrimination nature as a one-to-many relationship, it carries out variable selection at the individual level so that possible inherent group structure is ignored. In order to make the most of information implied in the group structure, this paper employs the exclusive lasso strategy to perform the similarity evaluation in two novel nearest-neighbor classification methods. Experimental results on both benchmark data sets and the face recognition problem demonstrate that the EL-based kNN method outperforms certain state-of-the-art classification techniques and existing representation-based nearest-neighbor approaches, in terms of both the size of feature reduction and the classification accuracy.

show abstract