192 citations · 406 across the 11 of their papers we have counts for
4 papers · 1 filter
Quantifying the Effects of Enforcing Disentanglement on Variational Autoencoders
Momchil Peychev, Petar Veličković, Pietro Liò
The notion of disentangled autoencoders was proposed as an extension to the variational autoencoder by introducing a disentanglement parameter , controlling the learning pressur…
Graph Attention Networks
Petar Veličković, Guillem Cucurull, Arantxa Casanova +3
We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the short…
Cross-modal Recurrent Models for Weight Objective Prediction from Multimodal Time-series Data
Petar Veličković, Laurynas Karazija, Nicholas D. Lane +6
We analyse multimodal time-series data corresponding to weight, sleep and steps measurements. We focus on predicting whether a user will successfully achieve his/her weight objecti…
XFlow: Cross-modal Deep Neural Networks for Audiovisual Classification
Cătălina Cangea, Petar Veličković, Pietro Liò
In recent years, there have been numerous developments towards solving multimodal tasks, aiming to learn a stronger representation than through a single modality. Certain aspects o…