Скачать с ютуб Improving Generalization in Molecular Modelling Through Organization and Augmentation - Huaxiu Yao в хорошем качестве

Improving Generalization in Molecular Modelling Through Organization and Augmentation - Huaxiu Yao

If you enjoyed this talk, consider joining the Molecular Modeling and Drug Discovery (M2D2) talks live: https://valence-discovery.github.io/M... Title: Improving Generalization in Low-resource molecular modelling through organization and augmentation Abstract: Meta-learning transfers knowledge across tasks and domains to learn new tasks efficiently, which has shown promise in drug discovery. However, the generalization ability of current meta-learning methods is limited by task heterogeneity and memorization. In this talk, I will first introduce two general principles to improve the generalization ability in meta-learning: organization and augmentation. Then, I will present several concrete few-shot drug discovery instantiations of using each principle. This includes algorithms to organize and adapt knowledge and a simple method for sufficiently overcoming task memorization. The remaining challenges and promising future research directions will also be discussed. Speaker: Huaxiu Yao - https://huaxiuyao.mystrikingly.com/ Twitter Prudencio:   / tossouprudencio   Twitter Therence:   / therence_mtl   Twitter Cas:   / cas_wognum   Twitter Valence Discovery:   / valence_ai   ~ Chapters: 00:00 Introduction: Meta-learning for drug discovery 06:35 Tackling the challenges through organization and augmentation 08:40 FRML (Organization: Task structure exploration) 21:28 FRML results 27:45 MetaMix (Augmentation: Regularizing Meta-learning algorithms) 37:25 MetaMix results 42:42 LISA (Discussion: Improving OOD robustness) 48:43 Q&A