Julius Sipilä
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Julius Sipilä has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Aadish Kumar Jain
Department of Computer Science, Aalto University, Espoo, Finland
1 shared publication - Heikki Käsnänen
Computational Medicine Design, Orion Pharma
1 shared publication - Markus Heinonen
Aalto University
1 shared publication Samuel Kaski
Department of Computer Science, Aalto University, Espoo, Finland
1 shared publication
Latest Publications
- Open Access
- 23 May 2025
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 6 (2) , 025042
Multi-target property prediction and optimization using latent spaces of generative model
Multi-target property prediction has the potential to improve generalization by exploiting the positive transfer between targets. Molecular generative models utilize independent single-target property prediction networks to discover novel molecules. We propose using multi-target networks to jointly predict several molecular properties and learn better representations by exploiting auxiliary information. Our multi-target model shows improvement in prediction accuracy on the test set. We additionally present results demonstrating promising performance in property prediction in these generative models does not translate to optimization. More specifically, random exploration is competitive with gradient-based strategies and better methods are needed.
- 23 May 2025
- Published by IOP Publishing in Machine Learning: Science and Technology
- Vol. 6 (2) , 025042
Open AccessMulti-target property prediction and optimization using latent spaces of generative model
Multi-target property prediction has the potential to improve generalization by exploiting the positive transfer between targets. Molecular generative models utilize independent single-target property prediction networks to discover novel molecules. We propose using multi-target networks to jointly predict several molecular properties and learn better representations by exploiting auxiliary information. Our multi-target model shows improvement in prediction accuracy on the test set. We additionally present results demonstrating promising performance in property prediction in these generative models does not translate to optimization. More specifically, random exploration is competitive with gradient-based strategies and better methods are needed.