Moment Matching Deep Contrastive Latent Variable Models

TL;DR

This paper introduces MM-cVAE, a novel contrastive VAE model that explicitly enforces latent variable constraints using moment matching, improving the discovery of target-specific patterns in contrastive analysis tasks.

Contribution

The paper proposes the moment matching contrastive VAE (MM-cVAE), which explicitly enforces latent variable constraints using maximum mean discrepancy, advancing contrastive latent variable modeling.

Findings

Outperforms previous models on three challenging CA tasks.

Qualitative and quantitative improvements over state-of-the-art.

Effectively isolates target-specific variations in datasets.

Abstract

In the contrastive analysis (CA) setting, machine learning practitioners are specifically interested in discovering patterns that are enriched in a target dataset as compared to a background dataset generated from sources of variation irrelevant to the task at hand. For example, a biomedical data analyst may seek to understand variations in genomic data only present among patients with a given disease as opposed to those also present in healthy control subjects. Such scenarios have motivated the development of contrastive latent variable models to isolate variations unique to these target datasets from those shared across the target and background datasets, with current state of the art models based on the variational autoencoder (VAE) framework. However, previously proposed models do not explicitly enforce the constraints on latent variables underlying CA, potentially leading to the undesirable leakage of information between the two sets of latent variables. Here we propose the moment matching contrastive VAE (MM-cVAE), a reformulation of the VAE for CA that uses the maximum mean discrepancy to explicitly enforce two crucial latent variable constraints underlying CA. On three challenging CA tasks we find that our method outperforms the previous state-of-the-art both qualitatively and on a set of quantitative metrics.