Adaptive multi-view subspace learning based on distributed optimization

Wei Guo

doi:10.1016/j.iot.2024.101203

Return

Adaptive multi-view subspace learning based on distributed optimization

2024-07-01

PRE

DOI：10.1016/j.iot.2024.101203

Original

Save

Abstract

En 中文

As the rapid development of Internet of Things (IoT), information is collected from different sensors and stored in distributed devices which can be regarded as the multi-view data. There are currently numerous clustering algorithms designed to handle multi-view data. However, most of these algorithms still suffer from the following problems: They are designed to operate directly on raw data, which preserves excessive redundant information. They primarily focus on pairwise relationships between views, neglecting the intricate high-order connections among multiple views. The prior information of singular values is not taken into account in multiple views and different views are considered to have equal contributions for clustering. To efficiently address above problems, adaptive multi-view subspace learning based on distributed optimization (AMSLDO) is proposed in this paper. Specifically, the original multi-view data is projected to a low-dimensional space for subspace representation, and multiple representation matrices are stacked in a tensor with weighted tensor nuclear norm to obtain high-order correlations and discover the prior information of singular values. Furthermore, the consensus matrix is learned from different representation matrices through adaptive weights. Meanwhile, samples are partitioned into the ideal number of clusters through Laplacian rank constraint. An efficient distributed optimization algorithm based on the Alternating Direction Method of Multipliers (ADMM) framework is designed to solve the proposed model. Extensive experiments are conducted on six datasets, demonstrating the superiority of the proposed model compared with eleven state-of-the-art methods.

Keywords:

Internet of Things

Multi-view data

Distributed optimization

Weighted tensor nuclear norm

Laplacian rank constraint