Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Reliable Conflictive Multi-View Learning

Cai Xu, Jiajun Si, Ziyu Guan, Wei Zhao, Yue Wu, Xiyue Gao

TL;DR

This work develops an Evidential Conflictive Multi-view Learning (ECML) method and theoretically proves this strategy can exactly model the relation of multi-view common and view-specific reliabilities for conflictive multi-view data.

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.

Reliable Conflictive Multi-View Learning

TL;DR

This work develops an Evidential Conflictive Multi-view Learning (ECML) method and theoretically proves this strategy can exactly model the relation of multi-view common and view-specific reliabilities for conflictive multi-view data.

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.
Paper Structure (19 sections, 14 equations, 5 figures, 3 tables)

This paper contains 19 sections, 14 equations, 5 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. The Method
  4. Problem Definition
  5. Evidential Conflictive Multi-view Learning
  6. View-specific Evidencial Deep Learning.
  7. Evidential Multi-view Fusion via Conflictive Opinion Aggregation.
  8. Loss Function.
  9. Discussion and Analyses
  10. Experiments
  11. Experimental Setup
  12. Datasets.
  13. Compared Methods.
  14. Experiment Results
  15. Performance Comparison.
  16. ...and 4 more sections

Figures (5)

  • Figure 1: Visualization of the conflictive multi-view data: the text view is related to food "sauce"; however, the other views show conflictive information, i.e., food "burger".
  • Figure 2: Illustration of ECML. View-specific DNNs collect evidence, which could be termed as the amount of support to each category. Then we form view-specific opinions consisting of belief masses of all categories and uncertainty (inverted to reliability). Finally, we integrate opinions by conflictive opinion aggregation. The uncertainty of the aggregated opinion might increase if view-specific opinions are conflictive.
  • Figure 3: Notations for conflictive multi-view data. The two categories are marked as yellow and green respectively. Conflictive instances contain noise and unalignment views: noise views are marked as blue and do not belong to any ground-truth categories; unaligned views show different categories from other views.
  • Figure 4: Conflictive degree visualization.
  • Figure 5: Density of uncertainty.