让生成模型的潜在空间随时间动态调整，提升持续优化效率。
Time-Aware Latent Space Bayesian Optimization
- 用带时间先验的变分自编码器建模时变目标下的潜在空间
- 在多个分子设计任务中，相比基线方法提升优化效果并保持稳定
- 适合长期迭代设计、目标会随时间变化的场景
潜在空间贝叶斯优化（LSBO）将贝叶斯优化扩展到分子设计等结构化领域，通过在生成模型的连续潜在空间中搜索实现。然而，多数LSBO方法假设目标函数固定，而实际设计过程中常出现目标漂移（如偏好变化或目标偏移）。将时变贝叶斯优化引入LSBO具有挑战性：漂移不仅影响代理模型，还可能改变由表示学习所诱导的潜在空间几何结构。本文提出时间感知潜在空间贝叶斯优化（TALBO），通过在代理模型和学习的生成表示中同时引入时间信息，利用带有高斯过程先验的变分自编码器，使潜在空间能随目标演化而对齐。为系统评估时变LSBO，我们改造了广泛使用的分子设计任务以适应漂移的多属性目标，并引入针对变化目标的专用评估指标。在多个基准测试中，TALBO始终优于强基线方法，在不同漂移速度和设计选择下均表现稳健，且在固定目标情况下仍保持竞争力。
原文摘要 · Abstract (English)
Latent-space Bayesian optimization (LSBO) extends Bayesian optimization to structured domains, such as molecular design, by searching in the continuous latent space of a generative model. However, most LSBO methods assume a fixed objective, whereas real design campaigns often face temporal drift (e.g., evolving preferences or shifting targets). Bringing time-varying BO into LSBO is nontrivial: drift can affect not only the surrogate, but also the latent search space geometry induced by the representation. We propose Time-Aware Latent-space Bayesian Optimization (TALBO), which incorporates time in both the surrogate and the learned generative representation via a GP-prior variational autoencoder, yielding a latent space aligned as objectives evolve. To evaluate timevarying LSBO systematically, we adapt widely used molecular design tasks to drifting multi-property objectives and introduce metrics tailored to changing targets. Across these benchmarks, TALBO consistently outperforms strong LSBO baselines and remains robust across drift speeds and design choices, while remaining competitive under actually time-invariant objectives.
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。