Topic Summary

Machine learning should not be accessible only to those who can pay. Specifically, modern machine learning is migrating to the era of complex models (e.g., deep neural networks), which emphasizes the data representation highly. This learning paradigm is known as representation learning. Specifically, via deep neural networks, learned representations often result in much better performance than can be obtained with hand-designed representations. It is noted that representation learning normally requires a plethora of well-annotated data. Giant companies have enough money to collect well-annotated data. Nonetheless, for startups or non-profit organizations, such data is barely acquirable due to the cost of labeling data or the intrinsic scarcity in the given domain. These practical issues motivate us to research and pay attention to weakly supervised representation learning (WSRL), since WSRL does not require such a huge amount of annotated data. We define WSRL as the collection of representation learning problem settings and algorithms that share the same goals as supervised representation learning but can only access to less supervised information than supervised representation learning. In this workshop, we discuss both theoretical and applied aspects of WSRL. Meanwhile, we will invite qualified submissions to Machine Learning Journal Special Issue on Weakly Supervised Representation Learning.

Topics of Interest

WSRL workshop includes but not limited to the following topics:

Topic Description

The focus of this workshop is five types of weak supervision: incomplete supervision, inexact supervision, inaccurate supervision, cross-domain supervision and imperfect demonstration. Specifically, incomplete supervision considers a subset of training data given with ground-truth labels while the other data remain unlabeled, such as semi-supervised representation learning and positive-unlabeled representation learning. Inexact supervision considers the situation where some supervision information is given but not as exacted as desired, i.e., only coarse-grained labels are available. For example, if we are considering to classify every pixel of an image, rather than the image itself, then ImageNet becomes a benchmark with inexact supervision. Besides, multi-instance representation learning belongs to inexact supervision, where we do not exactly know which instance in the bag corresponds to the given ground-truth label. Inaccurate supervision considers the situation where the supervision information is not always the ground-truth, such as label-noise representation learning.

Cross-domain supervision considers the situation where the supervision information is scarce or even non-existent in the current domain but can be possibly derived from other domains. Examples of cross-domain supervision appear in zero-/one-/few-shot representation learning, where external knowledge from other domains is usually used to overcome the problem of too few or even no supervision in the original domain. Imperfect demonstration considers the situation for inverse reinforcement representation learning and imitation representation learning, where the agent learns with imperfect or non-expert demonstrations. For example, AlphaGo learns a policy from a sequence of states and actions (expert demonstration). Even if an expert player wins a game, it is not guaranteed that every action in the sequence is optimal.

This workshop will discuss the fundamental theory of weakly supervised representation learning. Although theories of weakly supervised statistical learning already exist, extending these results for weakly supervised representation learning is still a challenge. Besides, this workshop also discusses on broad applications of weakly supervised representation learning, such as weakly supervised object detection (computer vision), weakly supervised sequence modeling (natural language processing), weakly supervised cross-media retrieval (information retrieval), and weakly supervised medical image segmentation (healthcare analysis).

Submission Guidelines

Papers should be formatted according to the IJCAI2021 formatting instructions for the Conference Track. The submissions with 2 pages will be considered for the poster, while the submissions with at least 4 pages will be considered for the oral presentation. Workshop submissions and camera ready versions will be handled by CMT. Please submit your paper to

IJCAI2021-WSRL is a non-archival venue and there will be no published proceedings. The papers will be posted on the workshop website. It will be possible to submit the IJCAI2021-WSRL submissions to other conferences and journals both in parallel to and after IJCAI2021-WSRL, if they accept such submissions. Besides, we also welcome submissions to IJCAI2021-WSRL that are under review at other conferences and workshops, if they allow concurrent submissions. At least one author from each accepted paper must register for the workshop. Please see the IJCAI 2021 Website for information about registration.

List of Invited Speakers

Sharon Li, University of Wisconsin-Madison (confirmed)

Paroma Varma, Snorkel AI (confirmed)

Yu-Feng Li, Nanjing University (confirmed)

Alex Ratner, University of Washington (confirmed)

Chang Xu, University of Sydney (confirmed)

Yang Liu, University of California Santa Cruz (confirmed)

Chunyuan Li, Microsoft Research, Redmond (confirmed)

Schedule and Zoom Recordings

The workshop will use UTC time for scheduling, and it will be combined with invited talks, contributed talks, and panel discussions.

Time (UTC) Event
00:00-00:05am Opening Ceremony
  Host: Masashi Sugiyama
00:05-00:35am Invited Talk 1
  Title: TBD
  Speaker: Alex Ratner
00:35-00:45am Contributed Talk 1
  Title: Autoencoding Slow Representations for Semi-supervised Data Efficient Regression
  Authors: Oliver Struckmeier, Kshitij Tiwari, and Ville Kyrki
00:45-1:15am Invited Talk 2
  Title: TBD
  Speaker: Sharon Li
1:15-1:25am Contributed Talk 2
  Title: A Weakly-Supervised Depth Estimation Network Using Attention Mechanism
  Authors: Fang Gao, wang jiabao, Jun Yu, yao xiong wang, and Feng Shuang
1:25-1:55am Invited Talk 3
  Title: TBD
  Speaker: Paroma Varma
1:55-2:05am Contributed Talk 3
  Title: Semi-Supervised Deep Ensembles for Blind Image Quality Assessment
  Authors: Zhihua Wang, Dingquan Li, and Kede Ma
2:05-2:35am Invited Talk 4
  Title: TBD
  Speaker: Yang Liu
2:35-2:45am Contributed Talk 4
  Title: Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
  Authors: Zhaowei Zhu, Yiwen Song, and Yang Liu
2:45-3:15am Invited Talk 5
  Title: TBD
  Speaker: Chang Xu
3:15-3:25am Contributed Talk 5
  Title: Learning from Crowds with Sparse and Imbalanced Annotations
  Authors: Ye Shi, Shao-Yuan Li, and Sheng-Jun Huang
3:25-3:55am Invited Talk 6
  Title: TBD
  Speaker: Yu-Feng Li
3:55-4:05am Contributed Talk 6
  Title: Property-aware Adaptive Relation Networks for Molecular Property Prediction
  Authors: Yaqing Wang, Abulikemu Abuduweili, and Dejing Dou
4:05-4:25am Invited Talk 7
  Title: Efficient Self-supervised Vision Transformers for Representation Learning
  Speaker: Chunyuan Li
4:25-4:50am Panel Discussion & Concluding Remark
  Host: Bo Han
  Guests: TBD

Important Dates

Submission Deadline: June 15th, 2021 (2nd Round)

Acceptance Notifications: June 25th, 2021


Bo Han, Hong Kong Baptist University, Hong Kong SAR, China.

Tongliang Liu, The University of Sydney, Australia.

Quanming Yao, Tsinghua University / 4Paradigm Inc., China.

Mingming Gong, The University of Melbourne, Australia.

Chen Gong, Nanjing University of Science and Technology, China.

Gang Niu, RIKEN, Japan.

Ivor W. Tsang, University of Technology Sydney, Australia.

Masashi Sugiyama, RIKEN / University of Tokyo, Japan.


Several awards are kindly sponsored by 4Paradigm Inc.

Previous Workshops

ACML2020 WSRL Workshop, Online.

SDM2020 WSUL Workshop, Ohio, United States.

ACML2019 WSL Workshop, Nagoya, Japan.