Incomplete multi-view clustering via local and global co-regularization

Liang, Jiye; Liu, Xiaolin; Bai, Liang; Cao, Fuyuan; Wang, Dianhui

doi:10.1007/s11432-020-3369-8

Cited by 7 publications

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, local representations that are constructed directly using a graph convolution network (GCN) are susceptible to high-frequency noise. Additionally, a global representation constructed from local representations of each view often only focuses on the consistency information of each view, effectively ignoring the complementary information [19].…”

Section: Introductionmentioning

confidence: 99%

Local-Global Representation Enhancement for Multi-View Graph Clustering

Zhao,

Hou,

Wang

2024

Electronics

View full text Add to dashboard Cite

In recent years, multi-view graph clustering algorithms based on representations learning have received extensive attention. However, existing algorithms are still limited in two main aspects, first, most algorithms employ graph convolution networks to learn the local representations, but the presence of high-frequency noise in these representations limits the clustering performance. Second, in the process of constructing a global representation based on the local representations, most algorithms focus on the consistency of each view while ignoring complementarity, resulting in lower representation quality. To address the aforementioned issues, a local-global representation enhancement for multi-view graph clustering algorithm is proposed in this paper. First, the low-frequency signals in the local representations are enhanced by a low-pass graph encoder, which yields smoother and more suitable local representations for clustering. Second, by introducing an attention mechanism, the local embedded representations of each view can be weighted and fused to obtain a global representation. Finally, to enhance the quality of the global representation, it is jointly optimized using the neighborhood contrastive loss and reconstruction loss. The final clustering results are obtained by applying the k-means algorithm to the global representation. A wealth of experiments have validated the effectiveness and robustness of the proposed algorithm.

show abstract

Section: Introductionmentioning

confidence: 99%