Bayesian Flow Is All You Need to Sample Out-of-Distribution Chemical Spaces
This addresses the problem of out-of-distribution generation in drug design, which is incremental as it builds on existing methods like diffusion models.
The paper tackles the challenge of generating novel molecules with higher properties than the training space for de novo drug design, showing that Bayesian flow networks can effortlessly produce high-quality out-of-distribution samples that surpass state-of-the-art models.
Generating novel molecules with higher properties than the training space, namely the out-of-distribution generation, is important for ${de~novo}$ drug design. However, it is not easy for distribution learning-based models, for example diffusion models, to solve this challenge as these methods are designed to fit the distribution of training data as close as possible. In this paper, we show that Bayesian flow network is capable of effortlessly generating high quality out-of-distribution samples that meet several scenarios. We introduce a semi-autoregressive training/sampling method that helps to enhance the model performance and surpass the state-of-the-art models.