DocumentCode :
3601719
Title :
Multi-View Intact Space Learning
Author :
Chang Xu ; Dacheng Tao ; Chao Xu
Author_Institution :
Lab. of Machine Perception, Peking Univ., Beijing, China
Volume :
37
Issue :
12
fYear :
2015
Firstpage :
2531
Lastpage :
2544
Abstract :
It is practical to assume that an individual view is unlikely to be sufficient for effective multi-view learning. Therefore, integration of multi-view information is both valuable and necessary. In this paper, we propose the Multi-view Intact Space Learning (MISL) algorithm, which integrates the encoded complementary information in multiple views to discover a latent intact representation of the data. Even though each view on its own is insufficient, we show theoretically that by combing multiple views we can obtain abundant information for latent intact space learning. Employing the Cauchy loss (a technique used in statistical learning) as the error measurement strengthens robustness to outliers. We propose a new definition of multi-view stability and then derive the generalization error bound based on multi-view stability and Rademacher complexity, and show that the complementarity between multiple views is beneficial for the stability and generalization. MISL is efficiently optimized using a novel Iteratively Reweight Residuals (IRR) technique, whose convergence is theoretically analyzed. Experiments on synthetic data and real-world datasets demonstrate that MISL is an effective and promising algorithm for practical applications.
Keywords :
image reconstruction; iterative methods; learning (artificial intelligence); IRR technique; MISL algorithm; Rademacher complexity; image reconstruction; iteratively reweight residuals technique; multi-view stability; multiview intact space learning; statistical learning; Algorithm design and analysis; Complexity theory; Learning systems; Loss measurement; Measurement uncertainty; Stability analysis; Statistical learning; Multi-view learning; robust algorithms;
fLanguage :
English
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
Publisher :
ieee
ISSN :
0162-8828
Type :
jour
DOI :
10.1109/TPAMI.2015.2417578
Filename :
7072521
Link To Document :
بازگشت