论文标题
反应预测的非自动回旋电子流量产生
Non-autoregressive electron flow generation for reaction prediction
论文作者
论文摘要
反应预测是计算化学中的一个基本问题。现有方法通常通过取样代币或图形依次编辑，以先前生成的输出为条件来产生化学反应。这些自回旋生成方法施加了任意排序的输出，并防止推理期间并行解码。我们设计了一种新颖的解码器，该解码器避免了这种顺序产生，并以非自动回归方式预测反应。受物理化学见解的启发，我们代表分子图中的边缘编辑作为电子流，然后可以并行预测。为了捕获反应的不确定性，我们引入了潜在变量以生成多模式输出。遵循以前的工作，我们在USPTO MIT数据集上评估了模型。我们的模型既达到了较低的推断潜伏期，均具有最先进的TOP-1准确性和在TOP-K采样方面的可比性。
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.
