Timezone: »

 
Poster
Towards understanding retrosynthesis by energy-based models
Ruoxi Sun · Hanjun Dai · Li Li · Steven Kearnes · Bo Dai

Thu Dec 09 04:30 PM -- 06:00 PM (PST) @
in Poster Session 7 »

Retrosynthesis is the process of identifying a set of reactants to synthesize a target molecule. It is of vital importance to material design and drug discovery. Existing machine learning approaches based on language models and graph neural networks have achieved encouraging results. However, the inner connections of these models are rarely discussed, and rigorous evaluations of these models are largely in need. In this paper, we propose a framework that unifies sequence- and graph-based methods as energy-based models (EBMs) with different energy functions. This unified view establishes connections and reveals the differences between models, thereby enhancing our understanding of model design. We also provide a comprehensive assessment of performance to the community. Moreover, we present a novel dual variant within the framework that performs consistent training to induce the agreement between forward- and backward-prediction. This model improves the state-of-the-art of template-free methods with or without reaction types.

Keywords: Deep Learning · Machine Learning · Graph Learning

Author Information

Ruoxi Sun (Google)
Hanjun Dai (Georgia Institute of Technology)
Li Li (Google)
Steven Kearnes (Google Research)
Bo Dai (Google Brain)

More from the Same Authors