← Search

Xinhai Ye

2 accepted papers

2024

RetroOOD: Understanding Out-of-Distribution Generalization in Retrosynthesis Prediction

AAAI 2024technical

Machine learning-assisted retrosynthesis prediction models have been gaining widespread adoption, though their performances oftentimes degrade significantly when deployed in real-world applications embracing out-of-distribution (OOD) molecules or reactions. Despite steady progress on standard benchm…

Cited by 4SourcePDFScholar
2022

The Role of Deconfounding in Meta-learning

ICML 2022spotlight

Meta-learning has emerged as a potent paradigm for quick learning of few-shot tasks, by leveraging the meta-knowledge learned from meta-training tasks. Well-generalized meta-knowledge that facilitates fast adaptation in each task is preferred; however, recent evidence suggests the undesirable memori…