Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2504.05318 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912314117062656 |
|---|---|
| author | Wang, Luyang Tang, Cangcheng Zhang, Chongyang Ruan, Jun Huang, Kai Dai, Jason |
| author_facet | Wang, Luyang Tang, Cangcheng Zhang, Chongyang Ruan, Jun Huang, Kai Dai, Jason |
| contents | Multi-task learning (MTL) is a common machine learning technique that allows the model to share information across different tasks and improve the accuracy of recommendations for all of them. Many existing MTL implementations suffer from scalability issues as the training and inference performance can degrade with the increasing number of tasks, which can limit production use case scenarios for MTL-based recommender systems. Inspired by the recent advances of large language models, we developed an end-to-end efficient and scalable Generalist Recommender (GRec). GRec takes comprehensive data signals by utilizing NLP heads, parallel Transformers, as well as a wide and deep structure to process multi-modal inputs. These inputs are then combined and fed through a newly proposed task-sentence level routing mechanism to scale the model capabilities on multiple tasks without compromising performance. Offline evaluations and online experiments show that GRec significantly outperforms our previous recommender solutions. GRec has been successfully deployed on one of the largest telecom websites and apps, effectively managing high volumes of online traffic every day. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05318 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Efficient Multi-Task Learning via Generalist Recommender Wang, Luyang Tang, Cangcheng Zhang, Chongyang Ruan, Jun Huang, Kai Dai, Jason Information Retrieval Artificial Intelligence Multi-task learning (MTL) is a common machine learning technique that allows the model to share information across different tasks and improve the accuracy of recommendations for all of them. Many existing MTL implementations suffer from scalability issues as the training and inference performance can degrade with the increasing number of tasks, which can limit production use case scenarios for MTL-based recommender systems. Inspired by the recent advances of large language models, we developed an end-to-end efficient and scalable Generalist Recommender (GRec). GRec takes comprehensive data signals by utilizing NLP heads, parallel Transformers, as well as a wide and deep structure to process multi-modal inputs. These inputs are then combined and fed through a newly proposed task-sentence level routing mechanism to scale the model capabilities on multiple tasks without compromising performance. Offline evaluations and online experiments show that GRec significantly outperforms our previous recommender solutions. GRec has been successfully deployed on one of the largest telecom websites and apps, effectively managing high volumes of online traffic every day. |
| title | Efficient Multi-Task Learning via Generalist Recommender |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2504.05318 |