Adversarial Canonical Correlation Analysis

05/20/2020
by   Benjamin Dutton, et al.
76

Canonical Correlation Analysis (CCA) is a statistical technique used to extract common information from multiple data sources or views. It has been used in various representation learning problems, such as dimensionality reduction, word embedding, and clustering. Recent work has given CCA probabilistic footing in a deep learning context and uses a variational lower bound for the data log likelihood to estimate model parameters. Alternatively, adversarial techniques have arisen in recent years as a powerful alternative to variational Bayesian methods in autoencoders. In this work, we explore straightforward adversarial alternatives to recent work in Deep Variational CCA (VCCA and VCCA-Private) we call ACCA and ACCA-Private and show how these approaches offer a stronger and more flexible way to match the approximate posteriors coming from encoders to much larger classes of priors than the VCCA and VCCA-Private models. This allows new priors for what constitutes a good representation, such as disentangling underlying factors of variation, to be more directly pursued. We offer further analysis on the multi-level disentangling properties of VCCA-Private and ACCA-Private through the use of a newly designed dataset we call Tangled MNIST. We also design a validation criteria for these models that is theoretically grounded, task-agnostic, and works well in practice. Lastly, we fill a minor research gap by deriving an additional variational lower bound for VCCA that allows the representation to use view-specific information from both input views.

READ FULL TEXT

page 15

page 25

page 26

page 27

page 28

page 30

research
03/09/2020

Variational Inference for Deep Probabilistic Canonical Correlation Analysis

In this paper, we propose a deep probabilistic multi-view model that is ...
research
10/30/2020

Multiview Variational Graph Autoencoders for Canonical Correlation Analysis

We present a novel multiview canonical correlation analysis model based ...
research
05/17/2021

Disentangled Variational Information Bottleneck for Multiview Representation Learning

Multiview data contain information from multiple modalities and have pot...
research
08/11/2017

Acoustic Feature Learning via Deep Variational Canonical Correlation Analysis

We study the problem of acoustic feature learning in the setting where w...
research
06/14/2021

Latent Correlation-Based Multiview Learning and Self-Supervision: A Unifying Perspective

Multiple views of data, both naturally acquired (e.g., image and audio) ...
research
11/21/2022

A Generalized EigenGame with Extensions to Multiview Representation Learning

Generalized Eigenvalue Problems (GEPs) encompass a range of interesting ...
research
08/29/2016

Linking Image and Text with 2-Way Nets

Linking two data sources is a basic building block in numerous computer ...

Please sign up or login with your details

Forgot password? Click here to reset