Deep generative models are at the core of research in Artificial Intelligence. They have achieved remarkable performance in many domains including computer vision, speech recognition, and audio synthesis. In recent years, they have infiltrated other fields of science including the natural sciences, physics, chemistry and molecular biology, and medicine. Despite these successes, deep generative models still face many challenges when they are used to model highly structured data such as natural language, video, and generic graph-structured data such as molecules. This workshop aims to bring experts from different backgrounds and perspectives to discuss the applications of deep generative models to these data modalities.

Relevant topics to this workshop include but are not limited to:

--Generative models for graphs, text, video, and other structured modalities
--Unsupervised representation learning of high dimensional structured data
--Learning and inference algorithms for deep generative models
--Evaluation methods for deep generative models
--Applications and practical implementations of deep generative models
--Scalable algorithms to accelerate learning with deep generative models
--Visualization methods for deep generative models
--Empirical analysis comparing different architectures for a given data modality