We invite submissions of papers studying the theory and practice of self-supervised learning. The topics include but are not limited to:
- Theoretical foundations of SSL
- Sample complexity of SSL methods
- Theory-driven design of auxiliary tasks in SSL
- Comparative analysis of different auxiliary tasks
- Comparative analysis of SSL and supervised approaches
- Information theory and SSL
- SSL for computer vision, natural language processing, robotics, speech processing, time-series analysis, graph analytics, etc.
- SSL for healthcare, social media, neuroscience, biology, social science, etc.
- Cognitive foundations of SSL
We invite submissions of full papers, as well as works-in-progress, position papers, and papers describing open problems and challenges. While original contributions are preferred, we also invite submissions of high-quality work that has recently been published in other venues or is concurrently submitted. Papers should be up to 4 pages in length (excluding references) formatted using the NeurIPS template. All the submissions should be anonymous. An optional appendix can be added in the submission, after references. There is no page limit for appendix. The accepted papers are allowed to get submitted to other conference venues. This workshop has no archival proceedings.
Papers can be submitted through CMT https://cmt3.research.microsoft.com/SSLNeurIPS2020
Paper submission deadline: 11:59 PM PST, Oct 10
Author notification: 11:59 PM PST, Oct 30
Camera-ready papers due: 11:59 PM PST, Nov 15