Research map / Probabilistic and scientific modeling / Variational and generative sampling
VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data
Chao Ma, Sebastian Tschiatschek, Richard Turner, José Miguel Hernández-Lobato, Cheng Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use VAEM's two-stage marginal and dependency VAEs instead of a single VAE | Mixed-type data generation · Bank, Boston, Avocado, Energy, and MIMIC | test NLL per variable | Mixed |
| Use VAEM's two-stage marginal and dependency VAEs instead of a single VAE | Conditional generation with missing entries · Bank, Boston, Avocado, Energy, and MIMIC | test NLL per variable | Mixed |
| Use VAEM for sequential active information acquisition | Mixed-type datasets · Bank and Avocado, and the other evaluated datasets | AUIC | Improved |
| Balance likelihood terms using adaptive constants | VAE · Conditional data generation across mixed-type datasets | test NLL per variable | Hurt |
Closest papers by meaning
- From Variational to Deterministic Autoencoders (ICLR 2020 · similarity 0.89)
- Learning Hierarchical Variational Autoencoders With Mutual Information Maximization for Autoregressive Sequence Modeling (TPAMI 2022 · similarity 0.88)
- Variational Autoencoder with Implicit Optimal Priors (AAAI 2019 · similarity 0.88)
- InfoVAE: Balancing Learning and Inference in Variational Autoencoders (AAAI 2019 · similarity 0.88)
- Trading Information between Latents in Hierarchical Variational Autoencoders (ICLR 2023 · similarity 0.88)
- Variational Mixture of HyperGenerators for Learning Distributions over Functions (ICML 2023 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
