Collaborative Diffusion Model for Recommender System
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912212906409984 |
|---|---|
| author | Lee, Gyuseok Zhu, Yaochen Yu, Hwanjo Zhou, Yao Li, Jundong |
| author_facet | Lee, Gyuseok Zhu, Yaochen Yu, Hwanjo Zhou, Yao Li, Jundong |
| contents | Diffusion-based recommender systems (DR) have gained increasing attention for their advanced generative and denoising capabilities. However, existing DR face two central limitations: (i) a trade-off between enhancing generative capacity via noise injection and retaining the loss of personalized information. (ii) the underutilization of rich item-side information. To address these challenges, we present a Collaborative Diffusion model for Recommender System (CDiff4Rec). Specifically, CDiff4Rec generates pseudo-users from item features and leverages collaborative signals from both real and pseudo personalized neighbors identified through behavioral similarity, thereby effectively reconstructing nuanced user preferences. Experimental results on three public datasets show that CDiff4Rec outperforms competitors by effectively mitigating the loss of personalized information through the integration of item content and collaborative signals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_18997 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Collaborative Diffusion Model for Recommender System Lee, Gyuseok Zhu, Yaochen Yu, Hwanjo Zhou, Yao Li, Jundong Information Retrieval Diffusion-based recommender systems (DR) have gained increasing attention for their advanced generative and denoising capabilities. However, existing DR face two central limitations: (i) a trade-off between enhancing generative capacity via noise injection and retaining the loss of personalized information. (ii) the underutilization of rich item-side information. To address these challenges, we present a Collaborative Diffusion model for Recommender System (CDiff4Rec). Specifically, CDiff4Rec generates pseudo-users from item features and leverages collaborative signals from both real and pseudo personalized neighbors identified through behavioral similarity, thereby effectively reconstructing nuanced user preferences. Experimental results on three public datasets show that CDiff4Rec outperforms competitors by effectively mitigating the loss of personalized information through the integration of item content and collaborative signals. |
| title | Collaborative Diffusion Model for Recommender System |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2501.18997 |