IAT: Instance-As-Token Compression for Historical User Sequence Modeling in Industrial Recommender Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910118455541760 |
|---|---|
| author | Li, Xinchun Zhang, Ning Yang, Qianqian Teng, Fei Zhao, Wenlin Yang, Huizhi Shi, Heng Chen, Linlan Wu, Yixin Wang, Zhen Hou, Daiye Qin, Fei Yu, Lele Tan, Yaocheng |
| author_facet | Li, Xinchun Zhang, Ning Yang, Qianqian Teng, Fei Zhao, Wenlin Yang, Huizhi Shi, Heng Chen, Linlan Wu, Yixin Wang, Zhen Hou, Daiye Qin, Fei Yu, Lele Tan, Yaocheng |
| contents | Although sophisticated sequence modeling paradigms have achieved remarkable success in recommender systems, the information capacity of hand-crafted sequential features constrains the performance upper bound. To better enhance user experience by encoding historical interaction patterns, this paper presents a novel two-stage sequence modeling framework termed Instance-As-Token (IAT). The first stage of IAT compresses all features of each historical interaction instance into a unified instance embedding, which encodes the interaction characteristics in a compact yet informative token. Both temporal-order and user-order compression schemes are proposed, with the latter better aligning with the demands of downstream sequence modeling. The second stage involves the downstream task fetching fixed-length compressed instance tokens via timestamps and adopting standard sequence modeling approaches to learn long-range preferences patterns. Extensive experiments demonstrate that IAT significantly outperforms state-of-the-art methods and exhibits superior in-domain and cross-domain transferability. IAT has been successfully deployed in real-world industrial recommender systems, including e-commerce advertising, shopping mall marketing, and live-streaming e-commerce, delivering substantial improvements in key business metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08933 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | IAT: Instance-As-Token Compression for Historical User Sequence Modeling in Industrial Recommender Systems Li, Xinchun Zhang, Ning Yang, Qianqian Teng, Fei Zhao, Wenlin Yang, Huizhi Shi, Heng Chen, Linlan Wu, Yixin Wang, Zhen Hou, Daiye Qin, Fei Yu, Lele Tan, Yaocheng Information Retrieval Although sophisticated sequence modeling paradigms have achieved remarkable success in recommender systems, the information capacity of hand-crafted sequential features constrains the performance upper bound. To better enhance user experience by encoding historical interaction patterns, this paper presents a novel two-stage sequence modeling framework termed Instance-As-Token (IAT). The first stage of IAT compresses all features of each historical interaction instance into a unified instance embedding, which encodes the interaction characteristics in a compact yet informative token. Both temporal-order and user-order compression schemes are proposed, with the latter better aligning with the demands of downstream sequence modeling. The second stage involves the downstream task fetching fixed-length compressed instance tokens via timestamps and adopting standard sequence modeling approaches to learn long-range preferences patterns. Extensive experiments demonstrate that IAT significantly outperforms state-of-the-art methods and exhibits superior in-domain and cross-domain transferability. IAT has been successfully deployed in real-world industrial recommender systems, including e-commerce advertising, shopping mall marketing, and live-streaming e-commerce, delivering substantial improvements in key business metrics. |
| title | IAT: Instance-As-Token Compression for Historical User Sequence Modeling in Industrial Recommender Systems |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2604.08933 |