GitHub

vae-cnn

PyTorch-based pipeline that trains a convolutional variational autoencoder on cat images, optionally tunes hyperparameters with Ray Tune, and samples new images by fitting a Gaussian Mixture Model in ...
IEEE

Dreaming Up Novel Quantum Dyes using Inverse Machine Learning in MatFlow

Abstract: Discovering novel molecules with targeted properties remains a formidable challenge in materials science, often likened to finding a needle in a haystack. Traditional experimental approaches ...
C&EN

MODAPro: Explainable Heterogeneous Networks with Variational Graph Autoencoder for Mining Disease-Specific Functional Molecules and Pathways from Omics Data

State Key Laboratory of Medical Proteomics, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, Dalian 116023, P. R. China University of Chinese Academy of Sciences, Beijing 100049, P.
IEEE

Multi-Metric Detection and Mitigation of Label-Flipping Attacks in Federated Learning Using Conditional Variational Autoencoders

Abstract: Federated Learning (FL) enables decentralized model training while preserving data privacy, but its distributed nature makes it vulnerable to data poisoning attacks. Among these, label ...