#artificial intelligence
May 2025
BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models
No existing model achieves strong generalization across all tasks: even the top-performing model exhibited an average OOD error 3x higher than in-distribution, so developing models with strong OOD generalization is a new frontier challenge in chemical ML.
Evan R. Antoniuk, Shehtab Zaman, Tal Ben-Nun et al.
· Neural Information Processin... · 14 citations
· ⚡1