Home History Schedule

Deep Generative Models for Highly Structured Data (ICLR 2022 Workshop)

(For any questions please email dgm4highlystructureddata@gmail.com)

Deep generative models are at the core of research in artificial intelligence, especially for unlabelled data. They have achieved remarkable performance in domains including computer vision, natural language processing, speech recognition, and audio synthesis. Very recently, deep generative models have been applied to broader domains, e.g. fields of science including the natural sciences, physics, chemistry and molecular biology, and medicine. However, deep generative models still face challenges when applied to these domains from which arise highly structured data. This workshop aims to bring experts from different backgrounds and perspectives to discuss the applications of deep generative models to these data modalities. The workshop will put an emphasis on challenges in encoding domain knowledge when learning representations, performing synthesis, or for prediction purposes. Since evaluation is essential for benchmarking, the workshop will also be a platform for discussing rigorous ways to evaluate representations and synthesis.

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

  • Generative models for graphs, time series, text, video, and other structured modalities.
  • Unsupervised representation learning of high dimensional structured data.
  • Learning and inference algorithms for deep generative models of structured data.
  • Applications and practical implementations of existing deep generative models to areas in science.
  • Scaling and improving graph neural networks for long-term dependencies in structured data.
  • Visualization methods for deep generative models of structured data.
  • Empirical analysis comparing different architectures for a given data modality and application.
  • Evaluation methods for representation and synthesis.
  • Important Dates

    Paper submission deadline25 Feb 7 March 2022
    Acceptance notification25 March 2022
    Camera-ready deadline15 April 2022
    Workshop29 April 2022


    We solicit 4-page paper (references not included) of high-quality contributions that are (1) originally published, or (2) recently published.

  • Submission Site: OpenReview
  • Style files and Templates: DGM4HSD ICLR 2022
  • Invited Speakers

    Max WellingUvA and Microsoft Research
    Octavian GaneaMassachusetts Institute of Technology
    Ellen ZhongMassachusetts Institute of Technology
    Pratyush TiwaryUniversity of Maryland
    Geemi WellawatteUniversity of Rochester


    Organizing Committee

    Yuanqi DuGeorge Mason University
    Adji Bousso DiengPrinceton University
    Yoon KimMassachusetts Institute of Technology
    Rianne van den BergMicrosoft Research
    Yoshua BengioMILA and Université de Montreal