Symmetric Nonnegative Matrix Factorization Based on Box-Constrained Half-Quadratic Optimization

Chen, Bo-Wei

doi:10.1109/access.2020.3023557

Cited by 6 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The number of nodes contained in the largest community in the network WebKB, Cora, Citeseer and Pubmed [40]. The specific parameters of the entire data set are shown in Table 3.…”

Section: Datasetmentioning

confidence: 99%

Graph Convolutional Networks based Non-Negative Matrix Factorization aware Community detection

Scholar

Professor

2023

Preprint

View full text Add to dashboard Cite

Nonnegative matrix factorization (NMF) is widely used in community discovery because of its effectiveness and easy interpretability. However, most of the existing NMF-based community detection methods are linear. They cannot effectively deal with the nonlinear characteristics of complex networks, resulting in further improvement in community detection performance. Aiming at this problem, a convolution graph network (GCN) enhanced nonlinear NMF community discovery method NMFGCN is proposed. NMFGCN consists of two main modules: GCN and NMF, where GCN is used to learn network node representations, and NMF uses node representations as input to obtain network community representations. In addition, a joint optimization method is proposed to train NMFGCN, which enables NMFGCN to have nonlinear feature representation capabilities and enables GCN and NMF to promote each other and obtain better community segmentation results. Many experiments on artificial synthetic networks and entire networks show that NMFGCN is superior to current NMF-based community discovery methods , thus proving that NMFGCN can improve the performance of NMF community discovery methods. In addition, NMFGCN also outperforms Deep Walk and LINE standard graph representation learning methods.

show abstract

“…The number of nodes contained in the largest community in the network WebKB, Cora, Citeseer and Pubmed [40]. The specific parameters of the entire data set are shown in Table 3.…”

Section: Datasetmentioning

confidence: 99%

Graph Convolutional Networks based Non-Negative Matrix Factorization aware Community detection

Scholar

Professor

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Traditional supervised learning deals with the analysis of single-label data, which means that samples are associated with a single label. However, in many realworld data mining applications, such as text classification [1,2], scene classification [3,4], crowd sensing/mining [5][6][7][8][9][10][11], and gene functional classification [12,13], the samples are associated with more than one label. From this description, we understand that the challenge of the multilabel classification task is its potential output.…”

Section: Introductionmentioning

confidence: 99%

Multilabel Classification Based on Graph Neural Networks

Ye¹,

Wang²

2022

Artificial Intelligence

View full text Add to dashboard Cite

Typical Laplacian embedding focuses on building Laplacian matrices prior to minimizing weights of connected graph components. However, for multilabel problems, it is difficult to determine such Laplacian graphs owing to multiple relations between vertices. Unlike typical approaches that require precomputed Laplacian matrices, this chapter presents a new method for automatically constructing Laplacian graphs during Laplacian embedding. By using trace minimization techniques, the topology of the Laplacian graph can be learned from input data, subsequently creating robust Laplacian embedding and influencing graph convolutional networks. Experiments on different open datasets with clean data and Gaussian noise were carried out. The noise level ranged from 6% to 12% of the maximum value of each dataset. Eleven different multilabel classification algorithms were used as the baselines for comparison. To verify the performance, three evaluation metrics specific to multilabel learning are proposed because multilabel learning is much more complicated than traditional single-label settings; each sample can be associated with multiple labels. The experimental results show that the proposed method performed better than the baselines, even when the data were contaminated by noise. The findings indicate that the proposed method is reliably robust against noise.

show abstract