DeepAI AI Chat
Log In Sign Up

Correlated Variational Auto-Encoders

by   Da Tang, et al.

Variational Auto-Encoders (VAEs) are capable of learning latent representations for high dimensional data. However, due to the i.i.d. assumption, VAEs only optimize the singleton variational distributions and fail to account for the correlations between data points, which might be crucial for learning latent representations from dataset where a priori we know correlations exist. We propose Correlated Variational Auto-Encoders (CVAEs) that can take the correlation structure into consideration when learning latent representations with VAEs. CVAEs apply a prior based on the correlation structure. To address the intractability introduced by the correlated prior, we develop an approximation by average of a set of tractable lower bounds over all maximal acyclic subgraphs of the undirected correlation graph. Experimental results on matching and link prediction on public benchmark rating datasets and spectral clustering on a synthetic dataset show the effectiveness of the proposed method over baseline algorithms.


page 1

page 2

page 3

page 4


Learning Correlated Latent Representations with Adaptive Priors

Variational Auto-Encoders (VAEs) have been widely applied for learning c...

Cross-modal Variational Auto-encoder with Distributed Latent Spaces and Associators

In this paper, we propose a novel structure for a cross-modal data assoc...

Variational auto-encoders with Student's t-prior

We propose a new structure for the variational auto-encoders (VAEs) prio...

Hyperbolic Graph Embedding with Enhanced Semi-Implicit Variational Inference

Efficient modeling of relational data arising in physical, social, and i...

Statistical Model Criticism of Variational Auto-Encoders

We propose a framework for the statistical evaluation of variational aut...

Spiking Variational Graph Auto-Encoders for Efficient Graph Representation Learning

Graph representation learning is a fundamental research issue and benefi...

Disentangling Disentanglement

We develop a generalised notion of disentanglement in Variational Auto-E...

Code Repositories


Synthetic gene expression data generation using Variational Auto-Encoder

view repo