Causal intervention for leveraging popularity bias in recommendation

Y Zhang, F Feng, X He, T Wei, C Song, G Ling… - Proceedings of the 44th …, 2021 - dl.acm.org
Recommender system usually faces popularity bias issues: from the data perspective, items
exhibit uneven (usually long-tail) distribution on the interaction frequency; from the method …

Elliot: A comprehensive and rigorous framework for reproducible recommender systems evaluation

VW Anelli, A Bellogín, A Ferrara, D Malitesta… - Proceedings of the 44th …, 2021 - dl.acm.org
Recommender Systems have shown to be an effective way to alleviate the over-choice
problem and provide accurate and tailored recommendations. However, the impressive …

Co-training disentangled domain adaptation network for leveraging popularity bias in recommenders

Z Chen, J Wu, C Li, J Chen, R Xiao… - Proceedings of the 45th …, 2022 - dl.acm.org
Recommender system usually faces popularity bias. From the popularity distribution shift
perspective, the normal paradigm trained on exposed items (most are hot items) identifies …

A flexible framework for evaluating user and item fairness in recommender systems

Y Deldjoo, VW Anelli, H Zamani, A Bellogin… - User Modeling and User …, 2021 - Springer
One common characteristic of research works focused on fairness evaluation (in machine
learning) is that they call for some form of parity (equality) either in treatment—meaning they …

A re-visit of the popularity baseline in recommender systems

Y Ji, A Sun, J Zhang, C Li - Proceedings of the 43rd International ACM …, 2020 - dl.acm.org
Popularity is often included in experimental evaluation to provide areference performance
for a recommendation task. To understand how popularity baseline is defined and …

Adversarial machine learning in recommender systems (aml-recsys)

Y Deldjoo, T Di Noia, FA Merra - … of the 13th International Conference on …, 2020 - dl.acm.org
Recommender systems (RS) are an integral part of many online services aiming to provide
an enhanced user-oriented experience. Machine learning (ML) models are nowadays …

Recommender systems fairness evaluation via generalized cross entropy

Y Deldjoo, VW Anelli, H Zamani, A Bellogín… - arXiv preprint arXiv …, 2019 - arxiv.org
Fairness in recommender systems has been considered with respect to sensitive attributes
of users (eg, gender, race) or items (eg, revenue in a multistakeholder setting). Regardless …

[PDF][PDF] Are We Forgetting Something? Correctly Evaluate a Recommender System With an Optimal Training Window.

R Verachtert, L Michiels, B Goethals - Perspectives@ RecSys, 2022 - ceur-ws.org
Recommender systems are deployed in dynamic environments with constantly changing
interests and availability of items, articles and products. The hyperparameter optimisation of …

On the discriminative power of hyper-parameters in cross-validation and how to choose them

VW Anelli, T Di Noia, E Di Sciascio, C Pomo… - Proceedings of the 13th …, 2019 - dl.acm.org
Hyper-parameters tuning is a crucial task to make a model perform at its best. However,
despite the well-established methodologies, some aspects of the tuning remain unexplored …

Irec: An interactive recommendation framework

T Silva, N Silva, H Werneck, C Mito… - Proceedings of the 45th …, 2022 - dl.acm.org
Nowadays, most e-commerce and entertainment services have adopted interactive
Recommender Systems (RS) to guide the entire journey of users into the system. This task …