Molecular graph generation is an emerging area of research with numerous applications. This problem remains challenging as molecular graphs are discrete, irregular, and permutation invariant to node order. Notably, most existing approaches fail to guarantee the intrinsic property of permutation invariance, resulting in unexpected bias in generative models. In this work, we propose GraphEBM to generate molecular graphs using energy-based models. In particular, we parameterize the energy function in a permutation invariant manner, thus making GraphEBM permutation invariant. We apply Langevin dynamics to train the energy function by approximately maximizing likelihood and generate samples with low energies. Furthermore, to generate molecules with a specific desirable property, we propose a simple yet effective strategy, which pushes down energies with flexible degrees according to the properties of corresponding molecules. Finally, we explore the use of GraphEBM for generating molecules with multiple objectives in a compositional manner. Comprehensive experimental results on random, goal-directed, and compositional generation tasks demonstrate the effectiveness of our proposed method.
翻译:分子图的生成是一个新兴的研究领域,应用了多种应用。这个问题仍然具有挑战性,因为分子图是离散的、不规律的和变异的,从节点顺序到节点顺序。值得注意的是,大多数现有方法都无法保证变异的内在特性,导致基因模型出现意想不到的偏差。在这项工作中,我们建议GreaphEBM用以能源为基础的模型生成分子图。特别是,我们以变异的方式对能量函数进行参数化,从而形成图形EBM变异式。我们运用Langevin动态来培训能源功能,大约使可能性最大化并产生低能量的样本。此外,为了产生具有特定可取特性的分子,我们提出了一个简单而有效的战略,根据相应分子的特性,以灵活的方式推低能量。最后,我们探索如何使用图形EBMM以组成方式生成具有多重目标的分子。关于随机、目标定向和组合生成任务的综合实验结果显示了我们拟议方法的有效性。