AI 中文总结
本文提出神经营斗流（Neural Petri Flow），一种在任意权重下保持Petri网语义的神经网络，用于化学反应中的原子映射、反应分类和产物预测，在多个基准上超越现有方法。
AI 中文摘要
Petri网已被用于描述化学反应过程，例如此http URL与化学的映射良好：位置是原子间的键和每个原子的自由价，令牌是键级单位，变迁形成或断裂键，守恒量是原子的价预算，使能规则是价规则。这些语义并不能由基于Petri网构建消息传递骨架的反应学习模型或神经网络所保证。在此，我们探讨何种架构在其权重取任意值时仍保持为Petri网。我们在理论中找到了答案，其中所有网的语义共享发射形式$m^\prime=m+C\sigma$、局部性（使能仅读取变迁的输入）以及使能规则，并且我们证明了守恒性强制了发射形式，非负性在局部速率定律上强制了使能规则。这留下了速率定律的自由，即每个变迁发射的倾向。我们引入了神经营斗流（Neural Petri Flow），它学习该速率定律，或用于分类的读出，并将其余部分硬接线为无参数层。在我们所称的价网（valence net）上，原子映射、反应分类和正向预测成为同一发射向量上的三个任务。无需训练，最小发射向量在精选的Golden集上映射88.8%，而RXNMapper为85.6%；在EnzymeMap的酶促反应上为88.7%对77.9%。在USPTO-480K上，基于这些发射向量训练的NPF预测了87.7%的产物，而在训练反应的1%子集上训练时预测了67.4%。ECREACT的EC编号在第三层级上预测了90.2%的反应，比已发表的最佳方法高出5.6个百分点。以电子为令牌，相同的令牌游戏首先预测了FlowER的90.5%基元步骤，优于已发表的基线，且每个top-1预测都是无需过滤的有效分子。
英文摘要
Petri nets have been used to describe chemical processes such as reactions.They map well to chemistry: Places are the bonds between atoms and the free valence of each atom, a token is a unit of bond order, a transition forms or breaks a bond, the conserved quantities are the valence budgets of the atoms, and the enabling rule is the valence rule. These semantics are not guaranteed by learned models of reactions or neural networks that are built on Petri nets that use the net as a scaffold for message passing. Here, we ask what architecture remains a Petri net for every value of its weights. We find the answer in the theory, where all semantics of a net share the firing form $m^\prime=m+Cσ$, locality, as enabling reads only the inputs of a transition, and the enabling rule, and we prove that conservation forces the firing form and that non-negativity forces the enabling rule on local rate laws. This leaves free the rate law, which is the propensity of each transition to fire. We introduce Neural Petri Flow, which learns this rate law, or a readout for classification, and hard-wires the rest as parameter-free layers. On what we denote a valence net, atom mapping, reaction classification, and forward prediction become three tasks on one firing vector. Without training, the minimum firing vector maps 88.8% of the curated Golden set against 85.6% for RXNMapper, and 88.7 against 77.9% of the enzymatic reactions of EnzymeMap. On USPTO-480K, NPF trained on these firing vectors predicts 87.7% of the products and 67.4% when trained on a 1% subset of the training reactions. EC numbers of ECREACT are predicted at the third level for 90.2% of reactions, 5.6 points ahead of the best published method. With electrons as tokens, the same token game predicts 90.5% of the elementary steps of FlowER first, ahead of the published baseline, and every top-1 prediction is a valid molecule without a filter.
Comments30 pages, 3 figures, 19 tables
