Uncorrelated Semi-paired Subspace Learning

TL;DR

This paper introduces a flexible semi-paired subspace learning framework that effectively utilizes unpaired multi-view data to learn uncorrelated features, improving performance in multi-view and multi-modality tasks.

Contribution

It proposes a generalized framework for uncorrelated multi-view subspace learning that incorporates semi-paired data, along with five new models and an efficient optimization method.

Findings

Models perform competitively or better than baselines.

Framework effectively handles unpaired multi-view data.

Experimental results demonstrate improved feature extraction and classification.

Abstract

Multi-view datasets are increasingly collected in many real-world applications, and we have seen better learning performance by existing multi-view learning methods than by conventional single-view learning methods applied to each view individually. But, most of these multi-view learning methods are built on the assumption that at each instance no view is missing and all data points from all views must be perfectly paired. Hence they cannot handle unpaired data but ignore them completely from their learning process. However, unpaired data can be more abundant in reality than paired ones and simply ignoring all unpaired data incur tremendous waste in resources. In this paper, we focus on learning uncorrelated features by semi-paired subspace learning, motivated by many existing works that show great successes of learning uncorrelated features. Specifically, we propose a generalized uncorrelated multi-view subspace learning framework, which can naturally integrate many proven learning criteria on the semi-paired data. To showcase the flexibility of the framework, we instantiate five new semi-paired models for both unsupervised and semi-supervised learning. We also design a successive alternating approximation (SAA) method to solve the resulting optimization problem and the method can be combined with the powerful Krylov subspace projection technique if needed. Extensive experimental results on multi-view feature extraction and multi-modality classification show that our proposed models perform competitively to or better than the baselines.