Implicit feedback (eg, clicks, dwell times, etc.) is an abundant source of data in human- interactive systems. While implicit feedback has many advantages (eg, it is inexpensive to …
A Singh, T Joachims - Advances in neural information …, 2019 - proceedings.neurips.cc
Abstract Conventional Learning-to-Rank (LTR) methods optimize the utility of the rankings to the users, but they are oblivious to their impact on the ranked items. However, there has …
A Singh, T Joachims - Proceedings of the 24th ACM SIGKDD …, 2018 - dl.acm.org
Rankings are ubiquitous in the online world today. As we have transitioned from finding books in libraries to ranking products, jobs, job applicants, opinions and potential romantic …
Rankings of people and items are at the heart of selection-making, match-making, and recommender systems, ranging from employment sites to sharing economy platforms. As …
In the past few years, there has been much work on incorporating fairness requirements into algorithmic rankers, with contributions coming from the data management, algorithms …
L Wang, T Joachims - Proceedings of the 2021 ACM SIGIR international …, 2021 - dl.acm.org
Ranking items by their probability of relevance has long been the goal of conventional ranking systems. While this maximizes traditional criteria of ranking performance, there is a …
Addressing unfairness in rankings has become an increasingly important problem due to the growing influence of rankings in critical decision making, yet existing learning-to-rank …
T Yang, Q Ai - Proceedings of the Web Conference 2021, 2021 - dl.acm.org
Rankings, especially those in search and recommendation systems, often determine how people access information and how information is exposed to people. Therefore, how to …
P Donmez, KM Svore, CJC Burges - Proceedings of the 32nd …, 2009 - dl.acm.org
A machine learning approach to learning to rank trains a model to optimize a target evaluation measure with repect to training data. Currently, existing information retrieval …