Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2604.07739 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914461122560000 |
|---|---|
| author | Jiao, Cathy Elenter, Juan Ravichandran, Praveen Huber, Bernd Cauteruccio, Joseph Wasson, Todd Heath, Timothy Xiong, Chenyan Lalmas, Mounia Bennett, Paul |
| author_facet | Jiao, Cathy Elenter, Juan Ravichandran, Praveen Huber, Bernd Cauteruccio, Joseph Wasson, Todd Heath, Timothy Xiong, Chenyan Lalmas, Mounia Bennett, Paul |
| contents | Recommendation systems must continuously adapt to evolving user behavior, yet the volume of data generated in large-scale streaming environments makes frequent full retraining impractical. This work investigates how targeted data selection can mitigate performance degradation caused by temporal distributional drift while maintaining scalability. We evaluate a range of representation choices and sampling strategies for curating small but informative subsets of user interaction data. Our results demonstrate that gradient-based representations, coupled with distribution-matching, improve downstream model performance, achieving training efficiency gains while preserving robustness to drift. These findings highlight data curation as a practical mechanism for scalable monitoring and adaptive model updates in production-scale recommendation systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_07739 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Efficient Dataset Selection for Continual Adaptation of Generative Recommenders Jiao, Cathy Elenter, Juan Ravichandran, Praveen Huber, Bernd Cauteruccio, Joseph Wasson, Todd Heath, Timothy Xiong, Chenyan Lalmas, Mounia Bennett, Paul Information Retrieval Machine Learning Recommendation systems must continuously adapt to evolving user behavior, yet the volume of data generated in large-scale streaming environments makes frequent full retraining impractical. This work investigates how targeted data selection can mitigate performance degradation caused by temporal distributional drift while maintaining scalability. We evaluate a range of representation choices and sampling strategies for curating small but informative subsets of user interaction data. Our results demonstrate that gradient-based representations, coupled with distribution-matching, improve downstream model performance, achieving training efficiency gains while preserving robustness to drift. These findings highlight data curation as a practical mechanism for scalable monitoring and adaptive model updates in production-scale recommendation systems. |
| title | Efficient Dataset Selection for Continual Adaptation of Generative Recommenders |
| topic | Information Retrieval Machine Learning |
| url | https://arxiv.org/abs/2604.07739 |