The ICML Workshop on Extreme Classification: Theory and Applications
17th July 2020
Extreme Delights


17th July 2020, 9:00AM – 7:00PM EST

The workshop will be held virtually due to travel restrictions associated with COVID-19.

*** Conference schedule, Poster Zoom Links etc. are available here ***

Invited speakers

Alina Beygelzimer (Yahoo! Research)
Inderjit Dhillon (UT Austin & Amazon)
Jure Leskovec (Stanford)
Maryam Majzoubi (NYU)
Tomas Mikolov (CIIRD Institute, Prague)
Manik Varma (MSR)
Chicheng Zhang (U Arizona)

Click on the above links for Talk Title, Talk Abstract and Speaker Bio.

Call for papers

Extreme classification is a rapidly growing research area focussing on multi-class and multi-label problems involving an extremely large number of labels. It brings many diverse approaches under the same umbrella including natural language processing (NLP), computer vision, information retrieval, recommendation systems, computational advertising, and embedding methods. Extreme classifiers have been deployed in many real-world applications in the industry ranging from language modelling to document tagging in NLP, face recognition to learning universal feature representations in computer vision, etc. Moreover, extreme classification finds application in recommendation, tagging, and ranking systems since these problems can be reformulated as multi-label learning tasks where each item to be ranked or recommended is treated as a separate label. Such reformulations have led to significant gains over traditional collaborative filtering and content-based recommendation techniques. Consequently, extreme classifiers have been deployed in many real-world applications in industry.

Extreme classification raises a number of interesting research questions including those related to:

  • Large scale learning and distributed and parallel training
  • Log-time and log-space prediction and prediction on a test-time budget
  • Label embedding and tree based approaches
  • Designing data structures for efficient learning such as trees, graphs or embeddings
  • Crowd sourcing, preference elicitation and other data gathering techniques
  • Bandits, semi-supervised learning and other approaches for dealing with training set biases and label noise
  • Bandits with an extremely large number of arms
  • Fine-grained classification
  • Zero shot learning and extensible output spaces
  • Tackling label polysemy, synonymy and correlations
  • Structured output prediction and multi-task learning
  • Learning from highly imbalanced data
  • Dealing with tail labels and learning from very few data points per label
  • PU learning and learning from missing and incorrect labels
  • Feature extraction, feature sharing, lazy feature evaluation, etc.
  • Performance evaluation
  • Statistical analysis and generalization bounds
  • Applications to new domains

The workshop aims to bring together researchers interested in these areas to encourage discussion and improve upon the state-of-the-art in extreme classification. In particular, we aim to bring together researchers from the natural language processing, computer vision and core machine learning communities to foster interaction and collaboration. Several leading researchers will present invited talks detailing the latest advances in the area. The workshop should be of interest to researchers in core supervised learning as well as application domains such as recommender systems, computer vision, computational advertising, information retrieval and natural language processing. We expect a healthy participation from both industry and academia.

Submission information

We solicit high-quality full papers that have not been published before in any other conferences or journals. The page limit for full papers is 8 pages without including references. We also allow submission of short abstracts of papers which have been published recently in case the authors seek more exposition for their work. The page limit for short abstracts is 4 pages without including references. For the short abstracts, please also provide a reference to the original full paper. All submissions will be considered for poster presentations. Some best quality submissions might also be considered for oral presentations. We will also have a best paper award.

Please submit full papers or short abstracts at XC20.

Submission deadline: Friday, 19th June 2020 (23:59 Pacific Time)

Author notification: 7th July 2020

All submissions must use the ICML template. Submissions should be in .pdf format. The review process is both single-blind and double-blind, so feel free to anonymize your submissions if so desired.


Anna Choromanska (NYU)
John Langford (MSR)
Maryam Majzoubi (NYU)
Yashoteja Prabhu (MSR)


Extreme classification resources

The Extreme Classification Repository: Multi-label Datasets and Code

Previous events

The CVPR 2020 Extreme Classification in Computer Vision Workshop
The 2018 Dagstuhl Seminar on Extreme Classification
The WWW 2018 Workshop on Extreme Multilabel Classification for Social Media
The NIPS 2017 Extreme Classification Workshop
The NIPS 2016 Extreme Classification Workshop
The NIPS 2015 Extreme Classification Workshop
The ICML 2015 Extreme Classification Workshop
The ECML/PKDD 2015 Workshop on Big Targets
The NIPS 2013 Extreme Classification Workshop
The Large-Scale Hierarchical Text Classification Challenge 2012-2014
The 2013 Machine Learning Summit