Home Accepted Papers Speakers

Deep Generative Models for Highly Structured Data (ICLR 2019 Workshop)

(For any questions please email deepgenstruct2019@gmail.com)

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, audio synthesis, and natural language processing. In recent years, they have also infiltrated other fields of science including the natural sciences, physics, chemistry, 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. These challenges include tractable algorithms for learning and inference, domain-specific parameterizations of generative models, rigorous evaluation of generative models, and more. This first workshop on Deep Generative Models for Highly Structured Data 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
  • Important Dates

    Paper submission deadlineMarch 26, 2019
    Acceptance notificationApril 20, 2019
    Camera-ready deadlineApril 27, 2019
    WorkshopMay 6, 2019

    Accepted Papers

    The accepted papers are available here, and the full proceedings is available on OpenReview.


    Location: Room R02
    3:15 - 3:30Introductory Remarks
    3:30 - 4:15Yoshua Bengio (Keynote)
    4:20 - 4:50Graham Neubig
    4:55 - 5:25Rose Yu
    5:30 - 6:00Yulia Tsvetkov
    6:05 - 6:35Aaron van den Oord
    6:40 - 7:30Poster Session + Dinner

    The full list of talk abstracts and speaker bios is available here.

    While the poster session unfortunately conflicts with the ICLR opening reception, we will have catered dinner during the poster session. Or feel free to go back and forth between the poster session and the reception!

    Invited Speakers

    Yoshua BengioMILA
    Rose YuNortheastern University
    Yulia TsvetkovCarnegie Mellon University
    Aaron van den OordDeepMind
    Graham NeubigCarnegie Mellon University


    Organizing Committee

    Adji Bousso Dieng Columbia University
    Yoon KimHarvard University
    Siva ReddyStanford University
    Kyunghyun ChoNew York University / Facebook
    Chris DyerDeepMind
    Phil BlunsomUniversity of Oxford / DeepMind
    David BleiColumbia University

    Program Committee

    • Martin Arjovsky
    • Urvashi Khandelwal
    • Elman Mansimov
    • Shashank Srivasta
    • Abigail See
    • Miltos Allamanis
    • Will Whitney
    • Jake Zhao
    • Andrew Miller
    • He He
    • Francisco Ruiz
    • Jianpeng Cheng
    • Dawen Liang
    • Luheng He
    • Li Dong
    • Will Grathwohl
    • Lea Frermann
    • Dieterich Lawson
    • Pengcheng Yin
    • Eunsol Choi
    • Shashi Narayan
    • Robin Jia
    • Akash Srivastava
    • Manzil Zaheer
    • Adams Wei Yu
    • David Pfau
    • Sander Dieleman
    • Mihaela Rosca
    • Theo Weber
    • Simon Shaolei Du
    • Michalis Titsias
    • Justin Chiu
    • Zhilin Yang
    • Wengong Jin
    • Yuntian Deng
    • Junxian He
    • Zhiting Hu
    • Zhe Gan
    • Jason Lee
    • Balaji Lakshminarayan
    • Da Tang
    • Tianxiao Shen


    dm fair fair