Multi-View Intact Space Learning
This work addresses the challenge of integrating multi-view data for improved representation learning, which is incremental as it builds on existing multi-view stability and generalization concepts.
The paper tackles the problem of insufficient individual views in multi-view learning by proposing the Multi-view Intact Space Learning (MISL) algorithm, which integrates complementary information from multiple views to discover a latent intact representation, and experiments on synthetic and real-world datasets demonstrate its effectiveness.
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.