Unbiased learning to rank (ULTR) methods aim to learn ranking models from biased user interactions, such as clicks. Given several impactful recent advancements in the field, our tutorial provides an introduction to the core concepts of ULTR and an overview of recent advancements in its foundations. We will give an overview of biases that ULTR methods can address, recent estimation techniques, and survey applications of ULTR, including fairness in ranking.Â
Our tutorial is intended to benefit both researchers and industry practitioners who are interested in developing new ULTR solutions or utilizing them in real-world applications.
Materials
Part I
Introduction, biases in user interactions,
and counterfactual estimation methods I.
Part II
Counterfactual estimation methods II,
survey of applications, and fair learning to rank.
Organizers
University of Amsterdam
University of Amsterdam
University of Amsterdam
University of Amsterdam
Radboud University