Foundation Models of Scientific Knowledge for Chemistry: Opportunities, Challenges and Lessons Learned

Sameera Horawalavithana, Ellyn Ayton, Shivam Sharma, Scott Howland, Megha Subramanian, Scott Vasquez, Robin Cosbey, Maria Glenski, Svitlana Volkova

Keywords: Large-Scale Language Models, Chemistry

Abstract:

Foundation models pre-trained on large corpora demonstrate significant gains across many natural language processing tasks and domains e.g., law, healthcare, education, etc. However, only limited efforts have investigated the opportunities and limitations of applying these powerful models to science and security applications. In this work, we develop foundation models of scientific knowledge for chemistry to augment scientists with the advanced ability to perceive and reason at scale previously unimagined. Specifically, we build large-scale (1.47B parameter) general-purpose models for chemistry that can be effectively used to perform a wide range of in-domain and out-of-domain tasks. Evaluating these models in a zero-shot setting, we analyze the effect of model and data scaling, knowledge depth, and temporality on model performance in context of model training efficiency.
Our novel findings demonstrate that (1) model size significantly contributes to the task performance when evaluated in a zero-shot setting; (2) data quality (aka diversity) affects model performance more than data quantity; (3) similarly, unlike previous work, temporal order of the documents in the corpus boosts model performance only for specific tasks, e.g., SciQ; and (4) models pre-trained from scratch perform better on in-domain tasks than those tuned from general-purpose models like Open AI's GPT-2.

TL;DR: We trained 25+ foundation models from scratch for chemistry and compared their performance on both in-domain and out-of-domain tasks over the OpenAI's GPT-2 models..