Publication Type
Conference Proceeding Article
Version
acceptedVersion
Publication Date
12-2022
Abstract
Recommender systems learn from historical user-item interactions to identify preferred items for target users. These observed interactions are usually unbalanced following a long-tailed distribution. Such long-tailed data lead to popularity bias to recommend popular but not personalized items to users. We present a gradient perspective to understand two negative impacts of popularity bias in recommendation model optimization: (i) the gradient direction of popular item embeddings is closer to that of positive interactions, and (ii) the magnitude of positive gradient for popular items are much greater than that of unpopular items. To address these issues, we propose a simple yet efficient framework to mitigate popularity bias from a gradient perspective. Specifically, we first normalize each user embedding and record accumulated gradients of users and items via popularity bias measures in model training. To address the popularity bias issues, we develop a gradient-based embedding adjustment approach used in model testing. This strategy is generic, model-agnostic, and can be seamlessly integrated into most existing recommender systems. Our extensive experiments on two classic recommendation models and four real-world datasets demonstrate the effectiveness of our method over state-of-the-art debiasing baselines.
Keywords
Training, Calibration, Data mining, Task analysis, Recommender systems, Optimization, Testing
Discipline
Databases and Information Systems | Data Storage Systems
Research Areas
Data Science and Engineering
Publication
2022 IEEE International Conference on Data Mining (ICDM): Orlando, FL, November 28 - December 1: Proceedings
First Page
438
Last Page
447
ISBN
9781665450997
Identifier
10.1109/ICDM54844.2022.00054
Publisher
IEEE Computer Society
City or Country
Los Alamitos, CA
Citation
REN, Weijieying; WANG, Lei; LIU, Kunpeng; GUO, Ruocheng; LIM, Ee-peng; and FU, Yanjie.
Mitigating popularity bias in recommendation with unbalanced interactions: A gradient perspective. (2022). 2022 IEEE International Conference on Data Mining (ICDM): Orlando, FL, November 28 - December 1: Proceedings. 438-447.
Available at: https://ink.library.smu.edu.sg/sis_research/7510
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1109/ICDM54844.2022.00054