Corpus ID: 153312821

Correlated Variational Auto-Encoders

@inproceedings{Tang2019CorrelatedVA,
  title={Correlated Variational Auto-Encoders},
  author={D. Tang and Dawen Liang and T. Jebara and N. Ruozzi},
  booktitle={ICML},
  year={2019}
}
  • D. Tang, Dawen Liang, +1 author N. Ruozzi
  • Published in ICML 2019
  • Computer Science, Mathematics
  • 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… CONTINUE READING
    11 Citations
    Learning Correlated Latent Representations with Adaptive Priors
    • 1
    • PDF
    Unsupervised Learning of Global Factors in Deep Generative Models
    • PDF
    The Autoencoding Variational Autoencoder
    • PDF
    The Functional Neural Process
    • 22
    • PDF
    Deep Variational Inference
    On the Equivalence between Node Embeddings and Structural Graph Representations
    • 19

    References

    SHOWING 1-10 OF 42 REFERENCES
    Variational Graph Auto-Encoders
    • 665
    • PDF
    beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework
    • 1,572
    Importance Weighted Autoencoders
    • 678
    • PDF
    Fixing a Broken ELBO
    • 235
    • PDF
    Auto-Encoding Variational Bayes
    • 10,491
    • PDF
    Variational Autoencoders for Collaborative Filtering
    • 270
    • PDF
    Improved Variational Inference with Inverse Autoregressive Flow
    • 840
    • PDF
    Interpretable VAEs for nonlinear group factor analysis
    • 14
    • PDF
    Variational Message Passing with Structured Inference Networks
    • 29
    • PDF
    Adam: A Method for Stochastic Optimization
    • 56,612
    • PDF