The Relevance of Item-Co-Exposure For Exposure Bias Mitigation

TL;DR

This study investigates how item-co-exposure influences exposure bias in recommender systems, demonstrating that discrete choice models effectively mitigate bias by considering item interactions, with implications for improving recommendation fairness.

Contribution

The paper extends previous work by validating discrete choice models on human data, comparing different models, and highlighting the importance of item-co-exposure in bias mitigation.

Findings

Discrete choice models effectively reduce exposure bias in human data.

No significant difference in robustness among different discrete choice models.

Multivariate models are robust to competition effects between items.

Abstract

Through exposing items to users, implicit feedback recommender systems influence the logged interactions, and, ultimately, their own recommendations. This effect is called exposure bias and it can lead to issues such as filter bubbles and echo chambers. Previous research employed the multinomial logit model (MNL) with exposure information to reduce exposure bias on synthetic data. This extended abstract summarizes our previous study in which we investigated whether (i) these findings hold for human-generated choices, (ii) other discrete choice models mitigate bias better, and (iii) an item's estimated relevance can depend on the relevances of the other items that were presented with it. We collected a data set of biased and unbiased choices in a controlled online user study and measured the effects of overexposure and competition. We found that (i) the discrete choice models effectively mitigated exposure bias on human-generated choice data, (ii) there were no significant differences in robustness among the different discrete choice models, and (iii) only multivariate discrete choice models were robust to competition between items. We conclude that discrete choice models mitigate exposure bias effectively because they consider item-co-exposure. Moreover, exposing items alongside more or less popular items can bias future recommendations significantly and item exposure must be tracked for overcoming exposure bias. We consider our work vital for understanding what exposure bias it, how it forms, and how it can be mitigated.