Uncertainty-Aware Multi-View Representation Learning

Authors

  • Yu Geng Tianjin University
  • Zongbo Han Tianjin University
  • Changqing Zhang Tianjin university Tianjin Key Lab of Machine Learning, Tianjin, China
  • Qinghua Hu Tianjin University Tianjin Key Lab of Machine Learning, Tianjin, China

Keywords:

Multi-instance/Multi-view Learning, Representation Learning

Abstract

Learning from different data views by exploring the underlying complementary information among them can endow the representation with stronger expressive ability. However, high-dimensional features tend to contain noise, and furthermore, quality of data usually varies for different samples (even for different views), i.e., one view may be informative for one sample but not the case for another. Therefore, it is quite challenging to integrate multi-view noisy data under unsupervised setting. Traditional multi-view methods either simply treat each view with equal importance or tune the weights of different views to fixed values, which are insufficient to capture the dynamic noise in multi-view data. In this work, we devise a novel unsupervised multi-view learning approach, termed as Dynamic Uncertainty-Aware Networks (DUA-Nets). Guided by the uncertainty of data estimated from the generation perspective, intrinsic information from multiple views is integrated to obtain noise-free representations. Under the help of uncertainty estimation, DUA-Nets weigh each view of individual sample according to data quality so that the high-quality samples (or views) can be fully exploited while the effects from the noisy samples (or views) will be alleviated. Our model achieves superior performance in extensive experiments and shows the robustness to noisy data.

Downloads

Published

2021-05-18

How to Cite

Geng, Y., Han, Z., Zhang, C., & Hu, Q. (2021). Uncertainty-Aware Multi-View Representation Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 35(9), 7545-7553. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16924

Issue

Section

AAAI Technical Track on Machine Learning II