167 citations · 357 across the 12 of their papers we have counts for
3 papers · 1 filter
Expressive Graph Informer Networks
Jaak Simm, Adam Arany, Edward De Brouwer +1
Applying machine learning to molecules is challenging because of their natural representation as graphs rather than vectors.Several architectures have been recently proposed for de…
GRU-ODE-Bayes: Continuous modeling of sporadically-observed time series
Edward De Brouwer, Jaak Simm, Adam Arany +1
Modeling real-world multidimensional time series can be particularly challenging when these are sporadically observed (i.e., sampling is irregular both in time and across dimension…
SMURFF: a High-Performance Framework for Matrix Factorization
Tom Vander Aa, Imen Chakroun, Thomas J. Ashby +10
Bayesian Matrix Factorization (BMF) is a powerful technique for recommender systems because it produces good results and is relatively robust against overfitting. Yet BMF is more c…