解耦VAE与高斯过程，提升分子优化效率
Return of the Latent Space COWBOYS: Re-thinking the use of VAEs for Bayesian Optimisation of Structured Spaces
- VAE与高斯过程独立训练，各司其职
- 在有限评估预算下更高效发现高潜力分子
- 适合需要结构化空间优化的研究者
基于变分自编码器（VAE）隐空间的贝叶斯优化是复杂结构化领域（如科学意义分子空间）优化任务的强大框架。然而，现有方法将代理模型与生成模型紧密耦合，当隐空间未针对特定任务定制时可能导致性能下降，从而催生出日益复杂的算法。本文提出一种新思路：解耦策略，分别训练生成模型（VAE）和高斯过程（GP）代理模型，再通过简单的贝叶斯更新规则结合。这种分离使各组件专注自身优势——VAE负责结构生成，GP负责预测建模。实验表明，该方法在有限评估预算下显著提升了分子优化中识别高潜力候选物的能力。
原文摘要 · Abstract (English)
Bayesian optimisation in the latent space of a Variational AutoEncoder (VAE) is a powerful framework for optimisation tasks over complex structured domains, such as the space of scientifically interesting molecules. However, existing approaches tightly couple the surrogate and generative models, which can lead to suboptimal performance when the latent space is not tailored to specific tasks, which in turn has led to the proposal of increasingly sophisticated algorithms. In this work, we explore a new direction, instead proposing a decoupled approach that trains a generative model and a Gaussian Process (GP) surrogate separately, then combines them via a simple yet principled Bayesian update rule. This separation allows each component to focus on its strengths -- structure generation from the VAE and predictive modelling by the GP. We show that our decoupled approach improves our ability to identify high-potential candidates in molecular optimisation problems under constrained evaluation budgets.
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。