Multi-clustering algorithm based on improved tensor chain decomposition
With the advent of the era of big data, the effective representation and analysis of high-level data has become a major challenge. Based on this, the application of tensor decomposition technology in multi-clustering algorithms was focused on especially for the processing of large multi-source heter...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | Chinese |
| Published: |
Beijing Xintong Media Co., Ltd
2025-06-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2025043/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | With the advent of the era of big data, the effective representation and analysis of high-level data has become a major challenge. Based on this, the application of tensor decomposition technology in multi-clustering algorithms was focused on especially for the processing of large multi-source heterogeneous datasets. The tensor train (TT) method was studied and improved in depth, which had significantly improved its performance in multi-clustering tasks by introducing a new optimization strategy. The innovations were mainly reflected in two aspects: firstly, a new tensor decomposition framework was proposed, which effectively reduced the storage cost and improved the computational efficiency by optimizing the objective function; secondly, the improved tensor decomposition technique was applied to three main multi-clustering algorithms, including self-weighted multi-view clustering (SwMC), latent multi-view subspace clustering (LMSC), and multi-view subspace clustering with intactness-aware similarity (MSC IAS), which significantly improved the accuracy and efficiency of clustering. To validate the effectiveness of the proposed methodology, comprehensive experiments were conducted on seven real-world datasets, including assessments of key metrics such as accuracy (ACC), normalized mutual information (NMI), and purity. Experimental results show that the proposed method has significant advantages in extracting meaningful patterns and improving clustering performance. |
|---|---|
| ISSN: | 1000-0801 |