Anchor graph has been recently proposed to accelerate multi-view graph clustering and widely applied in various large-scale applications. Different from capturing full instance relationships, these methods choose smal...
详细信息
Anchor graph has been recently proposed to accelerate multi-view graph clustering and widely applied in various large-scale applications. Different from capturing full instance relationships, these methods choose small portion anchors among each view, construct single-view anchor graphs and combine them into the unified graph. Despite its efficiency, we observe that: (i) Existing mechanism adopts a separable two-step procedure-anchor graph construction and individual graph fusion, which may degrade the clustering performance. (ii)These methods determine the number of selected anchors to be equal among all the views, which may destruct the data distribution diversity. A more flexible multi-view anchor graph fusion framework with diverse magnitudes is desired to enhance the representation ability. (iii) During the latter fusion process, current anchor graph fusion framework follows simple linearly-combined style while the intrinsic clustering structures are ignored. To address these issues, we propose a novel scalable and flexible anchor graph fusion framework for multi-view graph clustering method in this paper. Specially, the anchor graph construction and graph alignment are jointly optimized in our unified framework to boost clustering quality. Moreover, we present a novel structural alignment regularization to adaptively fuse multiple anchor graphs with different magnitudes. In addition, our proposed method inherits the linear complexity of existing anchor strategies respecting to the sample number, which is time-economical for large-scale data. Experiments conducted on various benchmark datasets demonstrate the superiority and effectiveness of the newly proposed anchor graph fusion framework against the existing state-of-the-arts over the clustering performance promotion and time expenditure. Our code is publicly available at https://***/wangsiwei2010/SMVAGC-SF.
Anchor-based multi-view graph clustering (AMVGC) has received abundant attention owing to its high efficiency and the capability to capture complementary structural information across multiple views. Intuitively, a hi...
详细信息
ISBN:
(纸本)9798400701085
Anchor-based multi-view graph clustering (AMVGC) has received abundant attention owing to its high efficiency and the capability to capture complementary structural information across multiple views. Intuitively, a high-quality anchor graph plays an essential role in the success of AMVGC. However, the existing AMVGC methods only consider single-structure information, i.e., local or global structure, which provides insufficient information for the learning task. To be specific, the over-scattered global structure leads to learned anchors failing to depict the cluster partition well. In contrast, the local structure with an improper similarity measure results in potentially inaccurate anchor assignment, ultimately leading to sub-optimal clustering performance. To tackle the issue, we propose a novel anchor-based multi-view graph clustering framework termed Efficient multi-view graph clustering with Local and Global Structure Preservation (EMVGC-LG). Specifically, a unified framework with a theoretical guarantee is designed to capture local and global information. Besides, EMVGC-LG jointly optimizes anchor construction and graph learning to enhance the clustering quality. In addition, EMVGC-LG inherits the linear complexity of existing AMVGC methods respecting the sample number, which is time-economical and scales well with the data size. Extensive experiments demonstrate the effectiveness and efficiency of our proposed method.
multi-view graph clustering has always been a representative multi-viewclustering method. The process of fusion of multiple views of the existing multi-view graph clustering method is performed on the basis of the si...
详细信息
ISBN:
(纸本)9781450385053
multi-view graph clustering has always been a representative multi-viewclustering method. The process of fusion of multiple views of the existing multi-view graph clustering method is performed on the basis of the similarity matrix. But the fusion method based on the similarity matrix does not deal with noise very well. Therefore, in this paper, an improved multi-view graph clustering based on tissue-like P System (IMGCP) method is proposed. IMGCP performs the view fusion operation on the basis of the embedded matrix F instead of on the basis of the similarity matrix. This will reduce the effect of noise on clustering performance. In addition, after obtaining the fused and updated embedding matrix, spectral rotation is performed on the embedding matrix instead of spectral clustering. At the same time, we put the IMGCP algorithm in the framework of the tissue-like P System to run. In this way, the computational parallelism of the tissue-like P System will be used to greatly improve the computational efficiency of IMGCP. Extensive experiments have verified the effectiveness of our algorithm.
multi-view graph clustering is an attentional research topic in recent years due to its wide applications. According to recent surveys, most existing works focus on incorporating comprehensive information among multip...
详细信息
multi-view graph clustering is an attentional research topic in recent years due to its wide applications. According to recent surveys, most existing works focus on incorporating comprehensive information among multiple views to achieve the clustering task. However, these studies pay less attention to explore the collaborative relationship between fusion-view features and independence-view features. To make full use of view relationships and enhance the complementary benefits of different views in graphs, we propose a trio-based collaborative learning framework for multi-viewgraph representation clustering (TCMGC) that drives the multiple auto-clustering constraints. We utilize the triplet operations (trio-based) to guarantee the independence and complementarity between each view and complete clustering tasks collaboratively. Meanwhile, we propose a joint optimization objective to improve the overall performance of representation learning and clustering. Experimental results on four real-world benchmark datasets show that the proposed TCMGC has promising performance compared with state-of-the-art baseline methods.
multi-view graph clustering has always been a representative multiviewclustering method. The process of fusion of multiple views of the existing multi-view graph clustering method is performed on the basis of the sim...
详细信息
multi-view graph clustering has always been a representative multiviewclustering method. The process of fusion of multiple views of the existing multi-view graph clustering method is performed on the basis of the similarity matrix. But the fusion method based on the similarity matrix does not deal with noise very well. Therefore, in this paper, an improved multi-view graph clustering based on tissuelike P System(IMGCP) method is proposed. IMGCP performs the view fusion operation on the basis of the embedded matrix F instead of on the basis of the similarity matrix. This will reduce the effect of noise on clustering performance. In addition, after obtaining the fused and updated embedding matrix, spectral rotation is performed on the embedding matrix instead of spectral clustering. At the same time, we put the IMGCP algorithm in the framework of the tissuelike P System to run. In this way, the computational parallelism of the tissue-like P System will be used to greatly improve the computational efficiency of IMGCP. Extensive experiments have verified the effectiveness of our algorithm.
multi-view graph clustering (MVGC) is a technique that combines information from multiple views to perform clustering analysis on graph data. However, the consensus information between the different views is not fully...
详细信息
multi-view graph clustering (MVGC) is a technique that combines information from multiple views to perform clustering analysis on graph data. However, the consensus information between the different views is not fully utilized. Additionally, the influence of noise is inevitable, leading to insufficient robustness of the algorithm. To address these issues, this paper proposes coupled double consensus multi-graph fusion for multi-viewclustering method (CDCMGF). Specifically, we first utilize the self-expressive property of the original data to obtain similarity graphs. Next, we further integrate the fusion of multiple similarity graphs into a consensus graph. However, the consensus information from different views is still not fully utilized, and there is some noise. Then, we utilize the self-expressive property of the consensus graph to obtain a much cleaner consensus graph. Fourth, we stack the two consensus graphs into a tensor, which is subjected to the constraint of the tensor nuclear norm (TNN). Then, the two consensus graphs reinforce each other, allowing for the comprehensive utilization of the consensus information from different views and reducing the influence of noise. Ultimately, by utilizing the augmented Lagrange multiplier method (ALM), the four steps outlined above are unified into a framework. The CDCMGF achieves a performance improvement of up to 64.86%, and the experimental results from various public datasets indicate that the CDCMGF algorithm outperforms the state-of-the-art algorithms. In other words, these experimental results validate the importance of fully utilizing the consensus information among the different views. The code is publicly available at https:// ***/TongWuahpu/CDCMGF.
暂无评论