Factor Graph Molecule Network for Structure Elucidation
This work tackles the problem of molecule structure elucidation, which is important for drug discovery, by proposing a new network architecture.
This paper addresses the challenge of learning molecule structures from physical/chemical properties, a task crucial for drug discovery. The authors propose a Factor Graph Molecule Network that integrates higher-order relational learning of Factor Graphs with Neural Networks, demonstrating effective factor learning and outperforming related methods.
Designing a network to learn a molecule structure given its physical/chemical properties is a hard problem, but is useful for drug discovery tasks. In this paper, we incorporate higher-order relational learning of Factor Graphs with strong approximation power of Neural Networks to create a molecule-structure learning network that has strong generalization power and can enforce higher-order relationship and valence constraints. We further propose methods to tackle problems such as the efficient design of factor nodes, conditional parameter sharing among factors, and symmetry problems in molecule structure prediction. Our experiment evaluation shows that the factor learning is effective and outperforms related methods.