4 papers
The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine Learning
Toby Boyne, Juan S. Campos, Becky D. Langdon +11
Machine learning has promised to change the landscape of laboratory chemistry, with impressive results in molecular property prediction and reaction retro-synthesis. However, chemi…
Limeade: Let integer molecular encoding aid
Shiqiang Zhang, Christian W. Feldmann, Frederik Sandfort +3
Mixed-integer programming (MIP) is a well-established framework for computer-aided molecular design (CAMD). By precisely encoding the molecular space and score functions, e.g., a g…
Verifying message-passing neural networks via topology-based bounds tightening
Christopher Hojny, Shiqiang Zhang, Juan S. Campos +1
Since graph neural networks (GNNs) are often vulnerable to attack, we need to know when we can trust them. We develop a computationally effective approach towards providing robust…
Augmenting optimization-based molecular design with graph neural networks
Shiqiang Zhang, Juan S. Campos, Christian Feldmann +3
Computer-aided molecular design (CAMD) studies quantitative structure-property relationships and discovers desired molecules using optimization algorithms. With the emergence of ma…