Deep Spectral Representation Learning From Multi-View Data

doi:10.1109/TIP.2021.3083072

Deep Spectral Representation Learning From Multi-View Data

2021-01-01

60

PRE

AI

DOI：10.1109/TIP.2021.3083072

Original

Original request for help

Save

Abstract

En 中文

Multi-view representation learning (MvRL) aims to learn a consensus representation from diverse sources or domains to facilitate downstream tasks such as clustering, retrieval, and classification. Due to the limited representative capacity of the adopted shallow models, most existing MvRL methods may yield unsatisfactory results, especially when the labels of data are unavailable. To enjoy the representative capacity of deep learning, this paper proposes a novel multi-view unsupervised representation learning method, termed as Multi-view Laplacian Network (MvLNet), which could be the first deep version of the multi-view spectral representation learning method. Note that, such an attempt is nontrivial because simply combining Laplacian embedding (i.e., spectral representation) with neural networks will lead to trivial solutions. To solve this problem, MvLNet enforces an orthogonal constraint and reformulates it as a layer with the help of Cholesky decomposition. The orthogonal layer is stacked on the embedding network so that a common space could be learned for consensus representation. Compared with numerous recent-proposed approaches, extensive experiments on seven challenging datasets demonstrate the effectiveness of our method in three multi-view tasks including clustering, recognition, and retrieval. The source code could be found at www.pengxi.me.

Keywords:

Deep learning

Laplace equations

Neural networks

Collaboration

Data models

Task analysis

Unsupervised multi-view representation learning

multi-view clustering

cross-modal retrieval

Deep Spectral Representation Learning From Multi-View Data

Abstract

AI Summary

Journal

Organization