Hi all, We’d like to invite you to submit to the NeurIPS 2021 Workshop on Distribution Shifts. Our workshop will be broadly about distribution shifts, and we will focus on bringing together applications and methods to facilitate discussion on real-world distribution shifts. The deadline to submit papers is on October 8, with an option to sign up for the mentorship program by late September. Please see the workshop website https://sites.google.com/view/distshift2021/ for the full information, and feel free to reach out to distshift-workshop-2...@googlegroups.com if you have any questions. Thank you!
--- *Workshop objectives & call for papers* Distribution shifts—where a model is deployed on a data distribution different from what it was trained on—pose significant robustness challenges in real-world ML applications. Such shifts are often unavoidable in the wild and have been shown to substantially degrade model performance in applications such as biomedicine, wildlife conservation, sustainable development, robotics, education, and criminal justice. For example, models can systematically fail when tested on patients from different hospitals or people from different demographics. Through the workshop, we hope to support and accelerate research on real-world distribution shifts. To this end, we will convene a diverse set of domain experts and methods-oriented researchers working on distribution shifts. We are broadly interested in methods, evaluations and benchmarks, and theory for distribution shifts, and we are especially interested in work on distribution shifts that arise naturally in real-world application contexts. Examples of relevant topics include, but are not limited to: - *Examples of real-world distribution shifts in various application areas. *We especially welcome applications that are not widely discussed in the ML research community, e.g., education, sustainable development, and conservation. - *Methods for improving robustness to distribution shifts. *Relevant settings include domain generalization, domain adaptation, and subpopulation shifts, and we are interested in a wide range of approaches, from uncertainty estimation to causal inference to active data collection. We welcome both general-purpose methods, as well as other methods that incorporate prior knowledge on the types of distribution shifts we wish to be robust on. We encourage evaluating these methods on real-world distribution shifts. - *Empirical and theoretical characterization of distribution shifts. *Distribution shifts can vary widely in the way in which the data distribution changes, as well as the empirical trends they exhibit. What empirical trends do we observe? What empirical or theoretical frameworks can we use to characterize these different types of shifts and their effects? What kinds of theoretical settings capture useful components of real-world distribution shifts? - *Benchmarks and evaluations.* We especially welcome contributions for subpopulation shifts, as they are underrepresented in current ML benchmarks. We are also interested in evaluation protocols that move beyond the standard assumption of fixed training and test splits -- for which applications would we need to consider other forms of shifts, such as streams of continually-changing data or feedback loops between models and data? *Speakers* - Aleksander Madry (MIT) - Chelsea Finn (Stanford University) - Elizabeth Tipton (Northwestern University) - Ernest Mwebaze (Makerere University & Sunbird AI) - Jonas Peters (University of Copenhagen) - Masashi Sugiyama (University of Tokyo) - Suchi Saria (Johns Hopkins University & Bayesian Health) *Panelists* - Andrew Beck (PathAI) - Jamie Morgenstern (University of Washington) - Judy Hoffman (Georgia Tech) - Tatsunori Hashimoto (Stanford University) *Organizers* - Shiori Sagawa (Stanford University) - Pang Wei Koh (Stanford University) - Fanny Yang (ETH Zurich) - Hongseok Namkoong (Columbia University) - Jiashi Feng (National University of Singapore) - Kate Saenko (Boston University) - Percy Liang (Stanford University) - Sarah Bird (Microsoft) - Sergey Levine (UC Berkeley)
_______________________________________________ uai mailing list uai@engr.orst.edu https://it.engineering.oregonstate.edu/mailman/listinfo/uai
