Mai Elkady — accepted AI-conference papers

2024

Vertical Validation: Evaluating Implicit Generative Models for Graphs on Thin Support Regions

Mai Elkady, Thu Bui, Bruno Ribeiro, David Inouye

UAI 2024poster

There has been a growing excitement that implicit graph generative models could be used to design or discover new molecules for medicine or material design. Because these molecules have not been discovered, they naturally lie in unexplored or scarcely supported regions of the distribution of known m…

Cited by 0 Source ↗PDF ↗Scholar ↗

2022

Discrete Tree Flows via Tree-Structured Permutations

Mai Elkady, Jim Lim, David I. Inouye

ICML 2022spotlight

While normalizing flows for continuous data have been extensively researched, flows for discrete data have only recently been explored. These prior models, however, suffer from limitations that are distinct from those of continuous flows. Most notably, discrete flow-based models cannot be straightfo…

Cited by 2 Source ↗PDF ↗Scholar ↗