Multiview Alignment and Generation in CCA via Consistent Latent Encoding
From MaRDI portal
Publication:3386409
Abstract: Multi-view alignment, achieving one-to-one correspondence of multi-view inputs, is critical in many real-world multi-view applications, especially for cross-view data analysis problems. Recently, an increasing number of works study this alignment problem with Canonical Correlation Analysis (CCA). However, existing CCA models are prone to misalign the multiple views due to either the neglect of uncertainty or the inconsistent encoding of the multiple views. To tackle these two issues, this paper studies multi-view alignment from the Bayesian perspective. Delving into the impairments of inconsistent encodings, we propose to recover correspondence of the multi-view inputs by matching the marginalization of the joint distribution of multi-view random variables under different forms of factorization. To realize our design, we present Adversarial CCA (ACCA) which achieves consistent latent encodings by matching the marginalized latent encodings through the adversarial training paradigm. Our analysis based on conditional mutual information reveals that ACCA is flexible for handling implicit distributions. Extensive experiments on correlation analysis and cross-view generation under noisy input settings demonstrate the superiority of our model.
Recommendations
Cites work
- scientific article; zbMATH DE number 3340881 (Why is no real title available?)
- A kernel two-sample test
- Advanced Lectures on Machine Learning
- Algorithmic Learning Theory
- Cross-Modal Localization via Sparsity
- Domain-adversarial training of neural networks
- Lectures on algebraic statistics
- Probabilistic Principal Component Analysis
- RELATIONS BETWEEN TWO SETS OF VARIATES
This page was built for publication: Multiview Alignment and Generation in CCA via Consistent Latent Encoding
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3386409)
