Academic Journal
Mitigating Spurious Correlations for Self-supervised Recommendation
| العنوان: | Mitigating Spurious Correlations for Self-supervised Recommendation |
|---|---|
| المؤلفون: | Lin, Xin-Yu, Xu, Yi-Yan, Wang, Wen-Jie, Zhang, Yang, Feng, Fu-Li |
| المصدر: | Machine Intelligence Research ; volume 20, issue 2, page 263-275 ; ISSN 2731-538X 2731-5398 |
| بيانات النشر: | Springer Science and Business Media LLC |
| سنة النشر: | 2023 |
| الوصف: | Recent years have witnessed the great success of self-supervised learning (SSL) in recommendation systems. However, SSL recommender models are likely to suffer from spurious correlations, leading to poor generalization. To mitigate spurious correlations, existing work usually pursues ID-based SSL recommendation or utilizes feature engineering to identify spurious features. Nevertheless, ID-based SSL approaches sacrifice the positive impact of invariant features, while feature engineering methods require high-cost human labeling. To address the problems, we aim to automatically mitigate the effect of spurious correlations. This objective requires to 1) automatically mask spurious features without supervision, and 2) block the negative effect transmission from spurious features to other features during SSL. To handle the two challenges, we propose an invariant feature learning framework, which first divides user-item interactions into multiple environments with distribution shifts and then learns a feature mask mechanism to capture invariant features across environments. Based on the mask mechanism, we can remove the spurious features for robust predictions and block the negative effect transmission via mask-guided feature augmentation. Extensive experiments on two datasets demonstrate the effectiveness of the proposed framework in mitigating spurious correlations and improving the generalization abilities of SSL models. |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | English |
| DOI: | 10.1007/s11633-022-1374-8 |
| DOI: | 10.1007/s11633-022-1374-8.pdf |
| DOI: | 10.1007/s11633-022-1374-8/fulltext.html |
| الاتاحة: | http://dx.doi.org/10.1007/s11633-022-1374-8 https://link.springer.com/content/pdf/10.1007/s11633-022-1374-8.pdf https://link.springer.com/article/10.1007/s11633-022-1374-8/fulltext.html |
| Rights: | https://creativecommons.org/licenses/by/4.0 ; https://creativecommons.org/licenses/by/4.0 |
| رقم الانضمام: | edsbas.1CF6A321 |
| قاعدة البيانات: | BASE |
| DOI: | 10.1007/s11633-022-1374-8 |
|---|