xuxu-wei/SUAVE
Implementation of a Hybrid Variational Autoencoder (VAE) for label information-guided dimensionality reduction and data synthesis.
This project helps data analysts and scientists make sense of complex, mixed-type datasets, like those found in healthcare or market research. It takes your raw data, including labels for specific outcomes, and transforms it into a more compact form while also being able to generate realistic new data points. You can use this to understand patterns better, predict outcomes, and create synthetic datasets for further analysis or sharing.
No commits in the last 6 months.
Use this if you need to reduce the complexity of mixed tabular data, generate synthetic samples that reflect the original data's characteristics, and predict outcomes using labels from your dataset.
Not ideal if your primary goal is simple, direct classification without needing data synthesis, dimensionality reduction, or handling diverse data types within a single model.
Stars
47
Forks
3
Language
Python
License
—
Last pushed
Oct 08, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/xuxu-wei/SUAVE"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Naresh1318/Adversarial_Autoencoder
A wizard's guide to Adversarial Autoencoders
mseitzer/pytorch-fid
Compute FID scores with PyTorch.
acids-ircam/RAVE
Official implementation of the RAVE model: a Realtime Audio Variational autoEncoder
ratschlab/aestetik
AESTETIK: Convolutional autoencoder for learning spot representations from spatial...
jaanli/variational-autoencoder
Variational autoencoder implemented in tensorflow and pytorch (including inverse autoregressive flow)