[ Program (Schedule, Invited Speakers, Accepted Papers, Awards),
Topics, Submission, Organizers, Previous Workshops ]



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

Opening Ceremony
Host: Masashi Sugiyama
Invited Talk 1
Title: Programmatic Supervision for Data-Centric AI
Speaker: Alex Ratner
Contributed Talk 1
Title: Autoencoding Slow Representations for Semi-supervised Data Efficient Regression
Authors: Oliver Struckmeier, Kshitij Tiwari, and Ville Kyrki
Invited Talk 2
Title: Uncovering the Unknowns of Deep Neural Networks: Challenges and Opportunities
Speaker: Sharon Li
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
Invited Talk 3
Title: Automating Weak Supervision to Label Training Data
Speaker: Paroma Varma
Contributed Talk 3 (Best Paper Runner-up)
Title: Semi-Supervised Deep Ensembles for Blind Image Quality Assessment
Authors: Zhihua Wang, Dingquan Li, and Kede Ma
Invited Talk 4
Title: Learning from Noisy Labels: Some Lessons and Challenges
Speaker: Yang Liu
Contributed Talk 4 (Best Paper)
Title: Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels
Authors: Zhaowei Zhu, Yiwen Song, and Yang Liu
Invited Talk 5
Title: Revisiting Proxies for Unsupervised Disentangled Representation Learning
Speaker: Chang Xu
Contributed Talk 5
Title: Learning from Crowds with Sparse and Imbalanced Annotations
Authors: Ye Shi, Shao-Yuan Li, and Sheng-Jun Huang
Invited Talk 6
Title: OOD Example and New Label under Weakly Supervised Scenario
Speaker: Yu-Feng Li
Contributed Talk 6 (Best Paper Runner-up)
Title: Property-aware Adaptive Relation Networks for Molecular Property Prediction
Authors: Yaqing Wang, Abulikemu Abuduweili, and Dejing Dou
Invited Talk 7
Title: Efficient Self-supervised Vision Transformers for Representation Learning
Speaker: Chunyuan Li
Panel Discussion & Concluding Remark
Host: Bo Han
Guests: The organizers and speakers
Poster Session
GatherTown: The link will be provided during the Zoom meeting

Invited Speakers

Alex Ratner, University of Washington (confirmed)

Sharon Li, University of Wisconsin-Madison (confirmed)

Paroma Varma, Snorkel AI (confirmed)

Yang Liu, University of California Santa Cruz (confirmed)

Chang Xu, University of Sydney (confirmed)

Yu-Feng Li, Nanjing University (confirmed)

Chunyuan Li, Microsoft Research, Redmond (confirmed)

Accepted Papers


Best Paper

Clusterability as an Alternative to Anchor Points When Learning with Noisy Labels, by Zhaowei Zhu, Yiwen Song, and Yang Liu.

Best Paper Runner-ups

Semi-Supervised Deep Ensembles for Blind Image Quality Assessment, by Zhihua Wang, Dingquan Li, and Kede Ma.

Property-aware Adaptive Relation Networks for Molecular Property Prediction, by Yaqing Wang, Abulikemu Abuduweili, and Dejing Dou.



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:

Further Descriptions

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).



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 https://cmt3.research.microsoft.com/IJCAIWSRL2021

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.


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

Acceptance Notifications: June 25th, 2021


Program Chairs

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.

Workflow Chairs

Yu Yao, The University of Sydney, Australia.


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.