Sharpness-Aware Cross-Domain Recommendation to Cold-Start Users
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910557391552512 |
|---|---|
| author | Zeng, Guohang Zhang, Qian Zhang, Guangquan Lu, Jie |
| author_facet | Zeng, Guohang Zhang, Qian Zhang, Guangquan Lu, Jie |
| contents | Cross-Domain Recommendation (CDR) is a promising paradigm inspired by transfer learning to solve the cold-start problem in recommender systems. Existing state-of-the-art CDR methods train an explicit mapping function to transfer the cold-start users from a data-rich source domain to a target domain. However, a limitation of these methods is that the mapping function is trained on overlapping users across domains, while only a small number of overlapping users are available for training. By visualizing the loss landscape of the existing CDR model, we find that training on a small number of overlapping users causes the model to converge to sharp minima, leading to poor generalization. Based on this observation, we leverage loss-geometry-based machine learning approach and propose a novel CDR method called Sharpness-Aware CDR (SCDR). Our proposed method simultaneously optimizes recommendation loss and loss sharpness, leading to better generalization with theoretical guarantees. Empirical studies on real-world datasets demonstrate that SCDR significantly outperforms the other CDR models for cold-start recommendation tasks, while concurrently enhancing the model's robustness to adversarial attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_01931 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Sharpness-Aware Cross-Domain Recommendation to Cold-Start Users Zeng, Guohang Zhang, Qian Zhang, Guangquan Lu, Jie Information Retrieval Cross-Domain Recommendation (CDR) is a promising paradigm inspired by transfer learning to solve the cold-start problem in recommender systems. Existing state-of-the-art CDR methods train an explicit mapping function to transfer the cold-start users from a data-rich source domain to a target domain. However, a limitation of these methods is that the mapping function is trained on overlapping users across domains, while only a small number of overlapping users are available for training. By visualizing the loss landscape of the existing CDR model, we find that training on a small number of overlapping users causes the model to converge to sharp minima, leading to poor generalization. Based on this observation, we leverage loss-geometry-based machine learning approach and propose a novel CDR method called Sharpness-Aware CDR (SCDR). Our proposed method simultaneously optimizes recommendation loss and loss sharpness, leading to better generalization with theoretical guarantees. Empirical studies on real-world datasets demonstrate that SCDR significantly outperforms the other CDR models for cold-start recommendation tasks, while concurrently enhancing the model's robustness to adversarial attacks. |
| title | Sharpness-Aware Cross-Domain Recommendation to Cold-Start Users |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2408.01931 |