ICML 2024 is the Forty-first International Conference on Machine Learning organized in Wien, Austria at July 21 to July 27, 2024. Find below the paper that was accepted to the conference from Aalto University.
Accepted papers
In alphabetical order. Click the title to see the authors and the abstract.
Authors
Maksim Sinelnikov, Manuel Haussmann, Harri Lähdesmäki
Abstract
Longitudinal data are important in numerous fields, such as healthcare, sociology and seismology, but real-world datasets present notable challenges for practitioners because they can be high-dimensional, contain structured missingness patterns, and measurement time points can be governed by an unknown stochastic process. While various solutions have been suggested, the majority of them have been designed to account for only one of these challenges. In this work, we propose a flexible and efficient latent-variable model that is capable of addressing all these limitations. Our approach utilizes Gaussian processes to capture temporal correlations between samples and their associated missingness masks as well as to model the underlying point process. We construct our model as a variational autoencoder together with deep neural network parameterised encoder and decoder models, and develop a scalable amortised variational inference approach for efficient model training. We demonstrate competitive performance using both simulated and real datasets.
Department of Computer Science
cs.aalto.fi
School of Science
Science for tomorrow’s technology, innovations and businesses
- Published:
- Updated:
Read more news
In low-hierarchy organisations, even key policy issues are discussed in Slack
In a recent study, Aalto University alumn Lauri Pietinalho, a visiting scholar at New York University's Stern School of Business, and Frank Martela, an assistant professor at Aalto University, investigated how low-hierarchy organisations deal with shared policies in confrontational situations and how authority functions within them.
Getting bacteria into line
Physicists use magnetic fields to manipulate bacterial behaviour
Nordic researchers develop predictive model for cross-border COVID spread
The uniquely multinational and cross-disciplinary research was made possible by transparent data-sharing between Nordic countries.