Request-Only Optimization for Recommendation Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908490608410624 |
|---|---|
| author | Guo, Liang Li, Wei Liao, Lucy Cheng, Huihui Zhang, Rui Shi, Yu Wang, Yueming Huang, Yanzun Zhai, Keke Wang, Pengchao Shi, Timothy Cao, Xuan Wang, Shengzhi Cai, Renqin Gong, Zhaojie Vichare, Omkar Jian, Rui Gao, Leon Deng, Shiyan Liu, Xingyu Zhang, Xiong Li, Fu Xie, Wenlei Wen, Bin Li, Rui Fang, Lu Liu, Xing Zhai, Jiaqi |
| author_facet | Guo, Liang Li, Wei Liao, Lucy Cheng, Huihui Zhang, Rui Shi, Yu Wang, Yueming Huang, Yanzun Zhai, Keke Wang, Pengchao Shi, Timothy Cao, Xuan Wang, Shengzhi Cai, Renqin Gong, Zhaojie Vichare, Omkar Jian, Rui Gao, Leon Deng, Shiyan Liu, Xingyu Zhang, Xiong Li, Fu Xie, Wenlei Wen, Bin Li, Rui Fang, Lu Liu, Xing Zhai, Jiaqi |
| contents | Deep Learning Recommendation Models (DLRMs) represent one of the largest machine learning applications on the planet. Industry-scale DLRMs are trained with petabytes of recommendation data to serve billions of users every day. To utilize the rich user signals in the long user history, DLRMs have been scaled up to unprecedented complexity, up to trillions of floating-point operations (TFLOPs) per example. This scale, coupled with the huge amount of training data, necessitates new storage and training algorithms to efficiently improve the quality of these complex recommendation systems. In this paper, we present a Request-Only Optimizations (ROO) training and modeling paradigm. ROO simultaneously improves the storage and training efficiency as well as the model quality of recommendation systems. We holistically approach this challenge through co-designing data (i.e., request-only data), infrastructure (i.e., request-only based data processing pipeline), and model architecture (i.e., request-only neural architectures). Our ROO training and modeling paradigm treats a user request as a unit of the training data. Compared with the established practice of treating a user impression as a unit, our new design achieves native feature deduplication in data logging, consequently saving data storage. Second, by de-duplicating computations and communications across multiple impressions in a request, this new paradigm enables highly scaled-up neural network architectures to better capture user interest signals, such as Generative Recommenders (GRs) and other request-only friendly architectures. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_05640 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Request-Only Optimization for Recommendation Systems Guo, Liang Li, Wei Liao, Lucy Cheng, Huihui Zhang, Rui Shi, Yu Wang, Yueming Huang, Yanzun Zhai, Keke Wang, Pengchao Shi, Timothy Cao, Xuan Wang, Shengzhi Cai, Renqin Gong, Zhaojie Vichare, Omkar Jian, Rui Gao, Leon Deng, Shiyan Liu, Xingyu Zhang, Xiong Li, Fu Xie, Wenlei Wen, Bin Li, Rui Fang, Lu Liu, Xing Zhai, Jiaqi Information Retrieval Artificial Intelligence Deep Learning Recommendation Models (DLRMs) represent one of the largest machine learning applications on the planet. Industry-scale DLRMs are trained with petabytes of recommendation data to serve billions of users every day. To utilize the rich user signals in the long user history, DLRMs have been scaled up to unprecedented complexity, up to trillions of floating-point operations (TFLOPs) per example. This scale, coupled with the huge amount of training data, necessitates new storage and training algorithms to efficiently improve the quality of these complex recommendation systems. In this paper, we present a Request-Only Optimizations (ROO) training and modeling paradigm. ROO simultaneously improves the storage and training efficiency as well as the model quality of recommendation systems. We holistically approach this challenge through co-designing data (i.e., request-only data), infrastructure (i.e., request-only based data processing pipeline), and model architecture (i.e., request-only neural architectures). Our ROO training and modeling paradigm treats a user request as a unit of the training data. Compared with the established practice of treating a user impression as a unit, our new design achieves native feature deduplication in data logging, consequently saving data storage. Second, by de-duplicating computations and communications across multiple impressions in a request, this new paradigm enables highly scaled-up neural network architectures to better capture user interest signals, such as Generative Recommenders (GRs) and other request-only friendly architectures. |
| title | Request-Only Optimization for Recommendation Systems |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2508.05640 |