Exploring Popularity Bias in Session-based Recommendation

Autor:	Wang, Haowen
Rok vydání:	2023
Předmět:	Computer Science - Information Retrieval Computer Science - Artificial Intelligence Computer Science - Machine Learning
Druh dokumentu:	Working Paper
Popis:	Existing work has revealed that large-scale offline evaluation of recommender systems for user-item interactions is prone to bias caused by the deployed system itself, as a form of closed loop feedback. Many adopt the \textit{propensity} concept to analyze or mitigate this empirical issue. In this work, we extend the analysis to session-based setup and adapted propensity calculation to the unique characteristics of session-based recommendation tasks. Our experiments incorporate neural models and KNN-based models, and cover both the music and the e-commerce domain. We study the distributions of propensity and different stratification techniques on different datasets and find that propensity-related traits are actually dataset-specific. We then leverage the effect of stratification and achieve promising results compared to the original models. Comment: 10pages, 9 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2312.07855 Zobrazit plný text záznamu View this record from Arxiv