图前向分布匹配用于分子逆设计
Graph Forward Distribution Matching for Molecular Inverse Design
浏览论文内容
中文总结 AI 辅助
GraphFDM通过前向过程优化图扩散模型，实现多属性分子逆设计，降低MAE达53%，化学有效性超0.99，并泛化到分布外属性组合。
中文摘要 AI 辅助
在不牺牲化学有效性的前提下实现对多个属性的精确控制，仍然是分子逆设计中的一个核心挑战。现有的强化学习（RL）方法通过将**反向**采样视为一个序列策略，使用单一终端奖励来优化数百个耦合决策，从而对图扩散模型进行微调。这些方法常常面临不稳定性、有效性崩溃以及属性增益有限的问题。我们引入了GraphFDM（图前向分布匹配），一种新的用于图扩散的在线RL范式，它通过**前向**过程进行优化。GraphFDM利用有效生成来定义一个奖励倾斜的目标分布，该分布针对每个属性条件在图大小和分子结构上联合优化，将强化信号融入监督学习，而无需存储反向轨迹。我们推导出唯一的最优目标，证明了条件层面的改进保证，并展示了标准图扩散的固定图大小先验会留下一个不可约的匹配间隙。在多条件聚合物和小分子生成中，GraphFDM在每个目标属性上均取得了最低的平均绝对误差（MAE），相对于最强基线降低了高达53.0%，且化学有效性高于0.99。它还能泛化到分布外的属性组合。
英文摘要
Achieving precise control over multiple properties without sacrificing chemical validity remains a central challenge in molecular inverse design. Existing reinforcement learning (RL) methods fine-tune graph diffusion models by treating **reverse** sampling as a sequential policy, using a single terminal reward to optimize hundreds of coupled decisions. They often suffer from instability, validity collapse, and limited property gains. We introduce GraphFDM (Graph Forward Distribution Matching), a new online RL paradigm for graph diffusion that performs optimization through the **forward** process. GraphFDM uses valid generations to define a reward-tilted target distribution jointly optimized over graph size and molecular structure for each property condition, incorporating reinforcement signals into supervised learning without storing reverse trajectories. We derive the unique optimal target, prove a condition-wise improvement guarantee, and show that the fixed graph-size prior of standard graph diffusion leaves an irreducible matching gap. In multi-conditional polymer and small-molecule generation, GraphFDM achieves the lowest MAE on every target property, with reductions of up to 53.0\% relative to the strongest baselines and chemical validity above 0.99. It further generalizes to out-of-distribution property combinations.
