论文标题
模块化流：差分分子产生
Modular Flows: Differential Molecular Generation
论文作者
论文摘要
产生新分子是推进关键应用，例如药物发现和材料合成的基础。但是，流可以通过反转编码过程有效地产生分子，但是，现有的流量模型要么需要人工去量化或特定的节点/边缘订购，因此缺乏诸如置换不变性之类的desiderata，或者诱导编码和解码步骤之间的差异，这使得在Hoc Valicitive后校正后需要进行解码。我们基于以图形PDE耦合的节点ODES系统将新型的连续归一化e（3）等均衡流量阐明，该系统反复将局部调和与全球对齐密度。我们的模型可以用作通讯的时间网络，并在密度估计和分子产生的任务上产生最高的性能。特别是，我们生成的样品在标准QM9和ZINC250K基准测试方面都可以实现最新。
Generating new molecules is fundamental to advancing critical applications such as drug discovery and material synthesis. Flows can generate molecules effectively by inverting the encoding process, however, existing flow models either require artifactual dequantization or specific node/edge orderings, lack desiderata such as permutation invariance, or induce discrepancy between the encoding and the decoding steps that necessitates post hoc validity correction. We circumvent these issues with novel continuous normalizing E(3)-equivariant flows, based on a system of node ODEs coupled as a graph PDE, that repeatedly reconcile locally toward globally aligned densities. Our models can be cast as message-passing temporal networks, and result in superlative performance on the tasks of density estimation and molecular generation. In particular, our generated samples achieve state-of-the-art on both the standard QM9 and ZINC250K benchmarks.
