Results 31 to 40 of about 4,772,239 (326)

Coupled Variational Autoencoder

CoRR, 2023
ICML ...
Xiaoran Hao, Patrick Shafto
openaire   +4 more sources

Inverse QSAR: reversing descriptor-driven prediction pipeline using attention-based conditional variational autoencoder (ACoVAE) [PDF]

, 2022
In order to better formalize the notorious Inverse-QSAR problem (finding structures of given QSAR-predicted properties) is considered in this paper as a two-step process1,2,3 including (i) finding “seed” descriptor vectors corresponding to user ...
Gilles , Marcou, Alexandre, Varnek, Igor, Baskin, Timur , Madzhidov, Daniyar , Mazitov, Dragos , Horvath, William, Bort, Fanny, Bonachera, Arkadii, Lin   +8 more
core   +1 more source

Variational autoencoder-based chemical latent space for large molecular structures with 3D complexity

Communications Chemistry, 2023
The structural diversity of chemical libraries, which are systematic collections of compounds that have potential to bind to biomolecules, can be represented by chemical latent space. A chemical latent space is a projection of a compound structure into a
Toshiki Ochiai, Tensei Inukai, Manato Akiyama, Kairi Furui, M. Ohue, N. Matsumori, S. Inuki, Motonari Uesugi, Toshiaki Sunazuka, Kazuya Kikuchi, Hideaki Kakeya, Yasubumi Sakakibara   +11 more
semanticscholar   +1 more source

Semi-Supervised Adversarial Variational Autoencoder

Machine Learning and Knowledge Extraction, 2020
We present a method to improve the reconstruction and generation performance of a variational autoencoder (VAE) by injecting an adversarial learning. Instead of comparing the reconstructed with the original data to calculate the reconstruction loss, we ...
Ryad Zemouri
doaj   +1 more source

Variational autoencoder architecture.

, 2021
Variational autoencoder architecture.
Rafael Geraldeli Rossi (11873826), Marcos Paulo Silva Gôlo (11873823), Ricardo Marcondes Marcacini (10455141)   +2 more
core   +1 more source

Graph Regularized Variational Ladder Networks for Semi-Supervised Learning

IEEE Access, 2020
To tackle the problem of semi-supervised learning (SSL), we propose a new autoencoder-based deep model. Ladder networks (LN) is an autoencoder-based method for representation learning which has been successfully applied on unsupervised learning and semi ...
Cong Hu, Xiao-Ning Song
doaj   +1 more source

Nearest Neighbours Graph Variational AutoEncoder

Algorithms, 2023
Graphs are versatile structures for the representation of many real-world data. Deep Learning on graphs is currently able to solve a wide range of problems with excellent results.
Lorenzo Arsini, Barbara Caccia, Andrea Ciardiello, Stefano Giagu, Carlo Mancini Terracciano   +4 more
doaj   +1 more source

Overdispersed variational autoencoders [PDF]

2017 International Joint Conference on Neural Networks (IJCNN), 2017
The ability to fit complex generative probabilistic models to data is a key challenge in AI. Currently, variational methods are popular, but remain difficult to train due to high variance of the sampling methods employed. We introduce the overdispersed variational autoencoder and overdispersed importance weighted autoencoder, which combine ...
Harshil Shah, David Barber, Aleksandar Botev   +2 more
openaire   +1 more source

altosaar/variational-autoencoder: Canonical release

, 2021
Release to address requests for ...
Ilya V. Schurov, Jaan Altosaar, Mohamad H. Danesh, Nishant Shukla, Chris Hodapp   +4 more
core   +1 more source

Multiresolution equivariant graph variational autoencoder

Machine Learning: Science and Technology, 2023
In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders (MGVAE), the first hierarchical generative model to learn and generate graphs in a multiresolution and equivariant manner. At each resolution level, MGVAE employs higher
Truong Son Hy, Risi Kondor
doaj   +1 more source