Modern representation learning techniques like deep neural networks have had a major impact on a wide range of tasks, achieving new state-of-the-art performances on benchmarks using little or no feature engineering. However, these gains are often difficult to translate into real-world settings because they usually require massive hand-labeled training sets. Collecting such training sets by hand is often infeasible due to the time and expense of labeling data; moreover, hand-labeled training sets are static and must be completely relabeled when real-world modeling goals change.

Increasingly popular approaches for addressing this labeled data scarcity include using weak supervision---higher-level approaches to labeling training data that are cheaper and/or more efficient, such as distant or heuristic supervision, constraints, or noisy labels; multi-task learning, to effectively pool limited supervision signal; data augmentation strategies to express class invariances; and introduction of other forms of structured prior knowledge. An overarching goal of such approaches is to use domain knowledge and data resources provided by subject matter experts, but to solicit it in higher-level, lower-fidelity, or more opportunistic ways.

In this workshop, we examine these increasingly popular and critical techniques in the context of representation learning. While approaches for representation learning in the large labeled sample setting have become increasingly standardized and powerful, the same is not the case in the limited labeled data and/or weakly supervised case. Developing new representation learning techniques that address these challenges is an exciting emerging direction for research [e.g., 1, 2]. Learned representations have been shown to lead to models robust to noisy inputs, and are an effective way of exploiting unlabeled data and transferring knowledge to new tasks where labeled data is sparse.

In this workshop, we aim to bring together researchers approaching these challenges from a variety of angles. Specifically this includes:

  • Learning representations to reweight and de-bias weak supervision
  • Representations to enforce structured prior knowledge (e.g. invariances, logic constraints).
  • Learning representations for higher-level supervision from subject matter experts
  • Representations for zero and few shot learning
  • Representation learning for multi-task learning in the limited labeled setting
  • Representation learning for data augmentation
  • Theoretical or empirically observed properties of representations in the above contexts

The second LLD workshop continues the conversation from the 2017 NeurIPS Workshop on Learning with Limited Labeled Data. Our goal is to once again bring together researchers interested in this growing field. With funding support, we are excited to again organize best paper awards for the most outstanding submitted papers. We also will have seven distinguished and diverse speakers from a range of machine learning perspectives, a panel on where the most promising directions for future research are, and a discussion session on developing new benchmarks and other evaluations for these techniques.

The LLD workshop organizers are also committed to fostering a strong sense of inclusion for all groups at this workshop, and to help this concretely, aside from the paper awards, there will be funding for several travel awards specifically for traditionally underrepresented groups.

Our Sponsors

We warmly thanks our generous sponsors to support this event!

Brand Logo Brand Logo Brand Logo

Previous Event Images

Our Speakers

Finalization soon.

speaker img

Anima Anandkumar


speaker img

Joan Bruna

New York University

speaker img

Luna Dong


speaker img

Alon Halevy

University of Washington

speaker img

Luke Zettlemoyer

University of Washington

Stefano Ermon

Stanford University

Schedule Detail

Schedule tentative.

  • 8.30 AM


  • event speaker

    8.40 AM

    Invited Talk 1

    By ...
  • event speaker

    9.10 AM

    Invited Talk 2

    By ...
  • 9.40 AM

    Contributed Talk 1

    By ...
  • 9.55 AM

    1-minute poster spotlights

  • 10.30 AM

    Poster Session 1/Coffee break

  • event speaker

    11.00 AM

    Invited Talk 4

    By ...
  • event speaker

    11.30 AM

    Invited Talk 5

    By ...
  • 12.00 PM

    Lunch break

  • 2.00 PM

    Panel: “Domain Knowledge vs. Sample Efficiency: Where Should We Focus?”

  • 3.00 PM

    1-minute poster spotlights

  • 3.30 PM

    Poster Session 2/Coffee break

  • 4.00 PM

    Contributed Talk 2

    By ...
  • event speaker

    4.15 PM

    Invited Talk 6

    By ...
  • event speaker

    4.45 PM

    Invited Talk 7

    By ...
  • 5.15 PM

    Contributed Talk 3

    By ...
  • 5.30 PM

    Contributed Talk 4

    By ...
  • 5.45 PM

    Discussion Session: New Evaluations and Benchmarks with Limited Labeled Data

  • 6.15 PM

    Award Ceremony

  • 6.25 PM

    Closing Remarks


ICLR 2019, New Orleans, Louisiana

Ernest N. Morial Convention Center, New Orleans

Submission and important dates

Please format your papers using the standard ICLR 2019 style files. The page limit is 4 pages (excluding references). Please do not include author information, submissions must be made anonymous. All accepted papers will be presented as posters(poster dimensions: TBC), with exceptional submissions also presented as oral talks.

We are pleased to announce that our sponsors, Google, LumenAI and SFDS will provide both best paper awards (2 awards of $500 each) and travelling support for exceptional submissions.

Submission deadline:

March 24, 2019, 11.59pm, GMT+1

Submit my paper.

Notification of acceptance:

April 5, 2019

List of accepted papers.

Camera ready due:


Yes, cross-submissions are allowed, yet please clearly indicate if the submitted work has been presented somewhere else. Accepted papers will not be archived, thus submission does not preclude publications in other venues.
Email organizing chairs: lld2019[at]googlegroups[dot]com
Submissions are reviewed through a confidential double-blind process.
We strongly encourage at least one author per submission to attend the workshop to present in person, however due to registration difficulties this year, submissions with no attending authors will still be considered.

Accepted papers



  • Isabelle Augenstein
  • Stephen Bach
  • Matthew Blaschko
  • Eugene Belilovsky
  • Edouard Oyallon
  • Anthony Platanios
  • Alex Ratner
  • Christopher Re
  • Xiang Ren
  • Paroma Varma


We would like to thank all our reviewers.