Learning enhanced specific representations for multi-view feature learning

doi:10.1016/j.knosys.2023.110590

2023-07-01

PRE

Xiao‐Yuan Jing *

刘

刘伟 (Wei Liu)

DOI：10.1016/j.knosys.2023.110590

原文链接

原文求助

摘要

En 中文

Multi-view data has two basic characteristics: consensus property and complementary property, in which complementary information refers to all view-specific information. Inspired by the popular saying The whole is greater than the sum of its parts, we introduce the concepts of parts, sum of its partsand wholeinto multi-view feature learning. When view-specific information is regarded as the parts, the complementary information consisting of all view-specific information would correspond to the sum of its parts. To explore the wholeinformation, we propose the Learning Enhanced Specific Representations for Multi-view Feature Learning (MvESR) approach, which points to learning the enhanced view-specific information through beneficial interactions between views. Specifically, MvESR concatenates all view-specific representations as the suminformation. Based on the suminformation, MvESR obtains the enhanced view-specific information through an element-wise addition between view-specific representation and the sumrepresentation. Then the complementary information consisting of enhanced view-specific representations can be regarded as the whole. In addition, MvESR obtains cross-view consensus information between each pairwise views, then concatenates them as fused cross-view consensus information. Considering that different representations may have different contributions for classification, we design an adaptive-weighting loss fusion strategy for multi-view classification. Experimental results on six large-scale public datasets verify that the proposed approach outperforms the compared methods.(c) 2023 Elsevier B.V. All rights reserved.

Keyword:

Multi -view feature learning

Complementary information

Consensus information

Enhanced specific information

Adaptive -weighting loss fusion