Bias and debias in recommender system: A survey and future directions

J Chen, H Dong, X Wang, F Feng, M Wang… - ACM Transactions on …, 2023‏ - dl.acm.org
While recent years have witnessed a rapid growth of research papers on recommender
system (RS), most of the papers focus on inventing machine learning models to better fit …

Unbiased Learning to Rank: On Recent Advances and Practical Applications

S Gupta, P Hager, J Huang, A Vardasbi… - Proceedings of the 17th …, 2024‏ - dl.acm.org
Since its inception, the field of unbiased learning to rank (ULTR) has remained very active
and has seen several impactful advancements in recent years. This tutorial provides both an …

User modeling and user profiling: A comprehensive survey

E Purificato, L Boratto, EW De Luca - arxiv preprint arxiv:2402.09660, 2024‏ - arxiv.org
The integration of artificial intelligence (AI) into daily life, particularly through information
retrieval and recommender systems, has necessitated advanced user modeling and …

On (Normalised) Discounted Cumulative Gain as an Off-Policy Evaluation Metric for Top-n Recommendation

O Jeunen, I Potapov, A Ustimenko - Proceedings of the 30th ACM …, 2024‏ - dl.acm.org
Approaches to recommendation are typically evaluated in one of two ways:(1) via a
(simulated) online experiment, often seen as the gold standard, or (2) via some offline …

Can clicks be both labels and features? unbiased behavior feature collection and uncertainty-aware learning to rank

T Yang, C Luo, H Lu, P Gupta, B Yin, Q Ai - Proceedings of the 45th …, 2022‏ - dl.acm.org
Using implicit feedback collected from user clicks as training labels for learning-to-rank
algorithms is a well-developed paradigm that has been extensively studied and used in …

Safe deployment for counterfactual learning to rank with exposure-based risk minimization

S Gupta, H Oosterhuis, M de Rijke - … of the 46th International ACM SIGIR …, 2023‏ - dl.acm.org
Counterfactual learning to rank (CLTR) relies on exposure-based inverse propensity scoring
(IPS), a LTR-specific adaptation of IPS to correct for position bias. While IPS can provide …

Unifying online and counterfactual learning to rank: A novel counterfactual estimator that effectively utilizes online interventions

H Oosterhuis, M de Rijke - Proceedings of the 14th ACM international …, 2021‏ - dl.acm.org
Optimizing ranking systems based on user interactions is a well-studied problem. State-of-
the-art methods for optimizing ranking systems based on user interactions are divided into …

Fairness of exposure in light of incomplete exposure estimation

M Heuss, F Sarvi, M de Rijke - Proceedings of the 45th International ACM …, 2022‏ - dl.acm.org
Fairness of exposure is a commonly used notion of fairness for ranking systems. It is based
on the idea that all items or item groups should get exposure proportional to the merit of the …

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

P Hager, R Deffayet, JM Renders, O Zoeter… - Proceedings of the 47th …, 2024‏ - dl.acm.org
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 justified …

Unbiased learning-to-rank needs unconfounded propensity estimation

D Luo, L Zou, Q Ai, Z Chen, C Li, D Yin… - Proceedings of the 47th …, 2024‏ - dl.acm.org
The logs of the use of a search engine provide sufficient data to train a better ranker.
However, it is well known that such implicit feedback reflects biases, and in particular a …