collaborators
Showing cs.IRShow all

6 papers · 1 filter

cs.IR2025

CLAX: Fast and Flexible Neural Click Models in JAX

Philipp Hager, Onno Zoeter, Maarten de Rijke

CLAX is a JAX-based library that implements classic click models using modern gradient-based optimization. While neural click models have emerged over the past decade, complex clic…

cs.IR2025

Unidentified and Confounded? Understanding Two-Tower Models for Unbiased Learning to Rank (Extended Abstract)

Philipp Hager, Onno Zoeter, Maarten de Rijke

Additive two-tower models are popular learning-to-rank methods for handling biased user feedback in industry settings. Recent studies, however, report a concerning phenomenon: trai…

cs.IR2025

Unidentified and Confounded? Understanding Two-Tower Models for Unbiased Learning to Rank

Philipp Hager, Onno Zoeter, Maarten de Rijke

Additive two-tower models are popular learning-to-rank methods for handling biased user feedback in industry settings. Recent studies, however, report a concerning phenomenon: trai…

cs.IR2024

An Offline Metric for the Debiasedness of Click Models

Romain Deffayet, Philipp Hager, Jean-Michel Renders +1

A well-known problem when learning from user clicks are inherent biases prevalent in the data, such as position or trust bias. Click models are a common method for extracting infor…

cs.IR2024

Understanding the Effects of the Baidu-ULTR Logging Policy on Two-Tower Models

Morris de Haan, Philipp Hager

Despite the popularity of the two-tower model for unbiased learning to rank (ULTR) tasks, recent work suggests that it suffers from a major limitation that could lead to its collap…

cs.IR2024

Unbiased Learning to Rank Meets Reality: Lessons from Baidu's Large-Scale Search Dataset

Philipp Hager, Romain Deffayet, Jean-Michel Renders +2

Unbiased learning-to-rank (ULTR) is a well-established framework for learning from user clicks, which are often biased by the ranker collecting the data. While theoretically justif…