arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.12124physics.chem-phcs.LG
收藏

用于反应预测的非自回归电子流产生

Non-autoregressive electron flow generation for reaction prediction

Hangrui Bi, Hengyi Wang, Chence Shi, Jian Tang

摘要:

反应预测是计算化学中的一个基本问题。现有的方法通常通过顺序地对令牌或图形编辑进行采样来生成化学反应,以先前生成的输出为条件。这些自回归生成方法强加了任意的输出顺序,并防止在推理过程中的并行解码。我们设计了一种新的解码器,避免了这种顺序生成和预测的反应在一个非自回归的方式。受物理化学见解的启发,我们将分子图中的边缘编辑表示为电子流,然后可以并行预测。为了捕捉反应的不确定性,我们引入潜变量来生成多模态输出。在之前的工作之后,我们在USPTO MIT数据集上评估了我们的模型。我们的模型实现了一个数量级的低推理延迟,具有最先进的前1精度和Top-K采样的可比性能。

英文摘要:

Reaction prediction is a fundamental problem in computational chemistry. Existing approaches typically generate a chemical reaction by sampling tokens or graph edits sequentially, conditioning on previously generated outputs. These autoregressive generating methods impose an arbitrary ordering of outputs and prevent parallel decoding during inference. We devise a novel decoder that avoids such sequential generating and predicts the reaction in a Non-Autoregressive manner. Inspired by physical-chemistry insights, we represent edge edits in a molecule graph as electron flows, which can then be predicted in parallel. To capture the uncertainty of reactions, we introduce latent variables to generate multi-modal outputs. Following previous works, we evaluate our model on USPTO MIT dataset. Our model achieves both an order of magnitude lower inference latency, with state-of-the-art top-1 accuracy and comparable performance on Top-K sampling.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑