Reliable Conflictive Multi-View Learning

TL;DR

This paper introduces a new problem in multi-view learning called Reliable Conflictive Multi-view Learning (RCML), which aims to provide decisions and reliabilities for conflicting multi-view data, and proposes an Evidential Conflictive Multi-view Learning (ECML) method to address it.

Contribution

The paper formulates the RCML problem and develops the ECML method that learns view-specific evidence and fuses opinions considering reliabilities, with theoretical guarantees.

Findings

ECML effectively handles conflictive multi-view data.

Experimental results on 6 datasets verify ECML's effectiveness.

Theoretically proven conflictive opinion aggregation strategy.

Abstract

Multi-view learning aims to combine multiple features to achieve more comprehensive descriptions of data. Most previous works assume that multiple views are strictly aligned. However, real-world multi-view data may contain low-quality conflictive instances, which show conflictive information in different views. Previous methods for this problem mainly focus on eliminating the conflictive data instances by removing them or replacing conflictive views. Nevertheless, real-world applications usually require making decisions for conflictive instances rather than only eliminating them. To solve this, we point out a new Reliable Conflictive Multi-view Learning (RCML) problem, which requires the model to provide decision results and attached reliabilities for conflictive multi-view data. We develop an Evidential Conflictive Multi-view Learning (ECML) method for this problem. ECML first learns view-specific evidence, which could be termed as the amount of support to each category collected from data. Then, we can construct view-specific opinions consisting of decision results and reliability. In the multi-view fusion stage, we propose a conflictive opinion aggregation strategy and theoretically prove this strategy can exactly model the relation of multi-view common and view-specific reliabilities. Experiments performed on 6 datasets verify the effectiveness of ECML.