Search Results for author:
Found 25 papers, 18 papers with code
Estimating the Hessian Matrix of Ranking Objectives for Stochastic Learning to Rank with Gradient Boosted Trees
Stochastic learning to rank (LTR) is a recent branch in the LTR field that concerns the optimization of probabilistic ranking models.
Consolidating Ranking and Relevance Predictions of Large Language Models through Post-Processing
Our method takes both LLM generated relevance labels and pairwise preferences.
A Lightweight Method for Modeling Confidence in Recommendations with Learned Beta Distributions
Most Recommender Systems (RecSys) do not provide an indication of confidence in their decisions.
Recent Advances in the Foundations and Applications of Unbiased Learning to Rank
This tutorial provides both an introduction to the core concepts of the field and an overview of recent advancements in its foundations along with several applications of its methods.
Safe Deployment for Counterfactual Learning to Rank with Exposure-Based Risk Minimization
For the CLTR field, our novel exposure-based risk minimization method enables practitioners to adopt CLTR methods in a safer manner that mitigates many of the risks attached to previous methods.
Closing the Gender Wage Gap: Adversarial Fairness in Job Recommendation
We conclude that adversarial debiasing of word representations can increase real-world fairness of systems and thus may be part of the solution for creating fairness-aware recommendation systems.
The Bandwagon Effect: Not Just Another Bias
Optimizing recommender systems based on user interaction data is mainly seen as a problem of dealing with selection bias, where most existing work assumes that interactions from different users are independent.
Reaching the End of Unbiasedness: Uncovering Implicit Limitations of Click-Based Learning to Rank
Thus, in contrast with limitations that follow from explicit assumptions, our aim is to recognize limitations that the field is currently unaware of.
State Encoders in Reinforcement Learning for Recommendation: A Reproducibility Study
In response to these shortcomings, we reproduce and expand on the existing comparison of attention-based state encoders (1) in the publicly available debiased RL4Rec SOFA simulator with (2) a different RL method, (3) more state encoders, and (4) a different dataset.
Learning-to-Rank at the Speed of Sampling: Plackett-Luce Gradient Estimation With Minimal Computational Complexity
Plackett-Luce gradient estimation enables the optimization of stochastic ranking models within feasible time constraints through sampling techniques.
Doubly-Robust Estimation for Correcting Position-Bias in Click Feedback for Unbiased Learning to Rank
The prevalent approach to unbiased click-based learning-to-rank (LTR) is based on counterfactual inverse-propensity-scoring (IPS) estimation.
It Is Different When Items Are Older: Debiasing Recommendations When Selection Bias and User Preferences Are Dynamic
We theoretically show that in a dynamic scenario in which both the selection bias and user preferences are dynamic, existing debiasing methods are no longer unbiased.
Computationally Efficient Optimization of Plackett-Luce Ranking Models for Relevance and Fairness
Unlike existing approaches that are based on policy gradients, PL-Rank makes use of the specific structure of PL models and ranking metrics.
Robust Generalization and Safe Query-Specialization in Counterfactual Learning to Rank
We introduce the Generalization and Specialization (GENSPEC) algorithm, a robust feature-based counterfactual LTR method that pursues per-query memorization when it is safe to do so.
Learning from User Interactions with Rankings: A Unification of the Field
The goal of a ranking system is to help a user find the items they are looking for with the least amount of effort.
Unifying Online and Counterfactual Learning to Rank
With the introduction of the intervention-aware estimator, we aim to bridge the online/counterfactual LTR division as it is shown to be highly effective in both online and counterfactual scenarios.
When Inverse Propensity Scoring does not Work: Affine Corrections for Unbiased Learning to Rank
Our main contribution is a new estimator based on affine corrections: it both reweights clicks and penalizes items displayed on ranks with high trust bias.
Taking the Counterfactual Online: Efficient and Unbiased Online Evaluation for Ranking
LogOpt turns the counterfactual approach - which is indifferent to the logging policy - into an online approach, where the algorithm decides what rankings to display.
Policy-Aware Unbiased Learning to Rank for Top-k Rankings
We prove that the policy-aware estimator is unbiased if every relevant item has a non-zero probability to appear in the top-k ranking.
FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles
Model interpretability has become an important problem in machine learning (ML) due to the increased effect that algorithmic decisions have on humans.
Unbiased Learning to Rank: Counterfactual and Online Approaches
Through randomization the effect of different types of bias can be removed from the learning process.
To Model or to Intervene: A Comparison of Counterfactual and Online Learning to Rank from User Interactions
At the moment, two methodologies for dealing with bias prevail in the field of LTR: counterfactual methods that learn from historical data and model user behavior to deal with biases; and online methods that perform interventions to deal with bias but use no explicit user models.
Differentiable Unbiased Online Learning to Rank
Instead, its gradient is based on inferring preferences between document pairs from user clicks and can optimize any differentiable model.
Ranking for Relevance and Display Preferences in Complex Presentation Layouts
Existing learning to rank methods cannot handle such complex ranking settings as they assume that the display order is known beforehand.
Semantic Video Trailers
Our approach effectively captures the multimodal semantics of queries and videos using state-of-the-art deep neural networks and creates a summary that is both semantically coherent and visually attractive.
