Embedded Deep Bilinear Interactive Information and Selective Fusion for Multi-view Learning

TL;DR

This paper introduces a novel multi-view learning framework that enhances classification accuracy by embedding comprehensive intra-view and cross-view interactive information and employing an adaptive view fusion strategy.

Contribution

It proposes a unified framework integrating intra-view, cross-view bilinear interactions, and a dynamic view ensemble mechanism for improved multi-view classification.

Findings

Effective on six public datasets

Outperforms existing multi-view methods

Adaptive view weighting improves decision accuracy

Abstract

As a concrete application of multi-view learning, multi-view classification improves the traditional classification methods significantly by integrating various views optimally. Although most of the previous efforts have been demonstrated the superiority of multi-view learning, it can be further improved by comprehensively embedding more powerful cross-view interactive information and a more reliable multi-view fusion strategy in intensive studies. To fulfill this goal, we propose a novel multi-view learning framework to make the multi-view classification better aimed at the above-mentioned two aspects. That is, we seamlessly embed various intra-view information, cross-view multi-dimension bilinear interactive information, and a new view ensemble mechanism into a unified framework to make a decision via the optimization. In particular, we train different deep neural networks to learn various intra-view representations, and then dynamically learn multi-dimension bilinear interactive information from different bilinear similarities via the bilinear function between views. After that, we adaptively fuse the representations of multiple views by flexibly tuning the parameters of the view-weight, which not only avoids the trivial solution of weight but also provides a new way to select a few discriminative views that are beneficial to make a decision for the multi-view classification. Extensive experiments on six publicly available datasets demonstrate the effectiveness of the proposed method.