Shortening the Trajectories: Identity-Aware Gaussian Approximation for Efficient 3D Molecular Generation
This addresses efficiency bottlenecks for deploying state-of-the-art generative models in practical applications, representing an incremental improvement over existing acceleration techniques.
The paper tackles the high computational cost of Gaussian-based Probabilistic Generative Models by introducing a framework that shortens generative trajectories using a closed-form Gaussian approximation, achieving substantial improvements in sample quality and computational efficiency across multiple data modalities.
Gaussian-based Probabilistic Generative Models (GPGMs) generate data by reversing a stochastic process that progressively corrupts samples with Gaussian noise. While these models have achieved state-of-the-art performance across diverse domains, their practical deployment remains constrained by the high computational cost of long generative trajectories, which often involve hundreds to thousands of steps during training and sampling. In this work, we introduce a theoretically grounded and empirically validated framework that improves generation efficiency without sacrificing training granularity or inference fidelity. Our key insight is that for certain data modalities, the noising process causes data to rapidly lose its identity and converge toward a Gaussian distribution. We analytically identify a characteristic step at which the data has acquired sufficient Gaussianity, and then replace the remaining generation trajectory with a closed-form Gaussian approximation. Unlike existing acceleration techniques that coarsening the trajectories by skipping steps, our method preserves the full resolution of learning dynamics while avoiding redundant stochastic perturbations between `Gaussian-like' distributions. Empirical results across multiple data modalities demonstrate substantial improvements in both sample quality and computational efficiency.