用特征分布校准生成模型，让合成分子更像目标类药物。
Calibrating Generative Models to Feature Distributions with MMD Finetuning
- 通过最小化生成物与目标物的特征分布差异来微调模型。
- 在174种抗生素数据集上，既提升特征匹配度又保持分子化学有效性。
- 适用于蛋白质和DNA生成，支持多种生成模型结构。
生成模型虽能产出单个合理样本，但在关键特征分布上可能偏离目标集合。例如，预训练于广义类药化学空间的模型生成的分子，其特征可能与特定治疗类别（如已知抗生素）显著不同。直接在目标集上微调易过拟合，且无法控制匹配哪些特征。为此，本文提出核校准生成模型（kCGM），利用无偏得分函数估计器最小化生成物与目标物特征分布间的最大均值差异（MMD），并引入KL正则项以保持接近预训练模型。在包含174种抗生素的目标集上，直接微调牺牲了化学合理性以匹配特征分布，而kCGM在改善目标特征匹配的同时提升了化学有效性。进一步实验表明，kCGM可仅用特征级监督适配自回归、连续空间扩散及离散扩散模型，在蛋白质与DNA生成任务中表现良好。代码开源：https://github.com/smithhenryd/cgm。
原文摘要 · Abstract (English)
Generative models can produce individually plausible samples while deviating substantially from a target set in the distribution of key features. For example, a model pretrained on broad drug-like chemical space may generate molecules whose molecular features differ from those of a therapeutic class of interest, such as known antibiotics. Correcting such distributional miscalibration is challenging: direct finetuning on the target set can overfit and does not control which features are matched. To fill this gap, we introduce kernel Calibrating Generative Models (kCGM). kCGM minimizes a maximum mean discrepancy (MMD) between generated and target feature distributions using an unbiased score-function estimator, with KL regularization to remain close to the pretrained model. On a target set of 174 antibiotics, direct finetuning sacrifices chemical validity for feature-distribution matching, whereas kCGM improves target feature matching while increasing validity. We further demonstrate kCGM in protein and DNA generation tasks, showing it can adapt autoregressive, continuous-space diffusion, and discrete diffusion models using only feature-level supervision. Code is available at https://github.com/smithhenryd/cgm.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。