Speaker
Description
Addressing the challenge of Out-of-Distribution (OOD) multi-set generation, this paper introduces YonedaVAE, a novel equivariant deep generative model inspired by Category Theory, introducing Yoneda-Pooling mechanism. This approach presents a learnable Yoneda Embedding to encode the relationships between objects in a category, providing a dynamic and generalizable representation of complex relational data sets. YonedaVAE introduces a self-distilled set generator, capable of zero-shot creating sets with variable inter-event and intra-event cardinality, facilitated by the novel Adaptive top-p Sampling. We demonstrate that YonedaVAE can produce new point clouds with cardinalities well beyond the training data and achieve context extrapolation. Trained on low luminosity ultra-high-granularity data of PXD at Belle II, YonedaVAE can generate high luminosity valid signatures with the correct intra-event correlation without exposure to similar data during training. Being able to generalize to out-of-distribution samples, YonedaVAE stands as a valuable method for extrapolative multi-set generation tasks, including de novo protein design, Drug Discovery, and simulating geometry-independent detector responses beyond experimental limits.
