Time-Aware Latent Space Bayesian Optimization
This addresses time-varying optimization challenges in real-world design campaigns, such as evolving preferences in molecular design, though it is incremental by extending existing LSBO methods to handle drift.
The paper tackled the problem of temporal drift in latent-space Bayesian optimization for structured domains like molecular design, proposing TALBO to incorporate time in both the surrogate and generative representation, which consistently outperformed baselines across adapted benchmarks with drifting objectives.
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.