Revisiting Sampling Strategies for Molecular Generation

TL;DR

This paper explores various sampling strategies in diffusion models for molecular generation, revealing that a novel stochastic approach called StoMax consistently improves performance over traditional methods.

Contribution

The study introduces and evaluates a new sampling strategy, StoMax, demonstrating its superiority in molecular generation tasks compared to conventional methods.

Findings

StoMax outperforms default sampling methods in molecular generation.

Sampling choice significantly impacts generative model performance.

Principled sampling approaches can advance molecular design.

Abstract

Sampling strategies in diffusion models are critical to molecular generation yet remain relatively underexplored. In this work, we investigate a broad spectrum of sampling methods beyond conventional defaults and reveal that sampling choice substantially affects molecular generation performance. In particular, we identify a maximally stochastic sampling (StoMax), a simple yet underexplored strategy, as consistently outperforming default sampling methods for generative models DDPM and BFN. Our findings highlight the pivotal role of sampling design and suggest promising directions for advancing molecular generation through principled and more expressive sampling approaches.