Name
Title | ||
|---|---|---|
Connecting user and item perspectives in popularity debiasing for collaborative recommendation |
Abstract | ||
|---|---|---|
•We propose two new metrics for monitoring popularity bias in recommendation.•Pair- and point-wise optimizations emphasize popularity-biased recommendations.•We propose a mitigation procedure based on a new data sampling and regularization.•Treated models are less biased on popularity and better meet beyond-accuracy goals. |
Year | DOI | Venue |
|---|---|---|
2021 | 10.1016/j.ipm.2020.102387 | Information Processing & Management |
Keywords | DocType | Volume |
Recommender systems,Popularity bias,Beyond-accuracy | Journal | 58 |
Issue | ISSN | Citations |
1 | 0306-4573 | 6 |
PageRank | References | Authors |
0.60 | 0 | 3 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ludovico Boratto | 1 | 163 | 30.91 |
| Gianni Fenu | 2 | 92 | 27.81 |
| Mirko Marras | 3 | 17 | 7.27 |