Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.10471 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915933364158464 |
|---|---|
| author | Li, Guowen Zhang, Yuepeng Zhang, Shunyu Zhang, Yi Jiang, Xiaoze Wang, Yi Zhuo, Jingwei |
| author_facet | Li, Guowen Zhang, Yuepeng Zhang, Shunyu Zhang, Yi Jiang, Xiaoze Wang, Yi Zhuo, Jingwei |
| contents | Large-scale short-video search ranking models are typically trained on sparse co-occurrence signals over hashed item identifiers (HIDs). While effective at memorizing frequent interactions, such ID-based models struggle to generalize to long-tailed items with limited exposure. This memorization-generalization trade-off remains a longstanding challenge in such industrial systems. We propose SID-Coord, a lightweight Semantic ID framework that incorporates discrete, trainable semantic IDs (SIDs) directly into ID-based ranking models. Instead of treating semantic signals as auxiliary dense features, SID-Coord represents semantics as structured identifiers and coordinates HID-based memorization with SID-based generalization within a unified modeling framework. To enable effective coordination, SID-Coord introduces three components: (1) an attention-based fusion module over hierarchical SIDs to capture multi-level semantics, (2) a target-aware HID-SID gating mechanism that adaptively balances memorization and generalization, and (3) a SID-driven interest alignment module that models the semantic similarity distribution between target items and user histories. SID-Coord can be integrated into existing production ranking systems without modifying the backbone model. Online A/B experiments in a real-world production environment show statistically significant improvements, with a +0.664% gain in long-play rate in search and a +0.369% increase in search playback duration. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_10471 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SID-Coord: Coordinating Semantic IDs for ID-based Ranking in Short-Video Search Li, Guowen Zhang, Yuepeng Zhang, Shunyu Zhang, Yi Jiang, Xiaoze Wang, Yi Zhuo, Jingwei Information Retrieval Large-scale short-video search ranking models are typically trained on sparse co-occurrence signals over hashed item identifiers (HIDs). While effective at memorizing frequent interactions, such ID-based models struggle to generalize to long-tailed items with limited exposure. This memorization-generalization trade-off remains a longstanding challenge in such industrial systems. We propose SID-Coord, a lightweight Semantic ID framework that incorporates discrete, trainable semantic IDs (SIDs) directly into ID-based ranking models. Instead of treating semantic signals as auxiliary dense features, SID-Coord represents semantics as structured identifiers and coordinates HID-based memorization with SID-based generalization within a unified modeling framework. To enable effective coordination, SID-Coord introduces three components: (1) an attention-based fusion module over hierarchical SIDs to capture multi-level semantics, (2) a target-aware HID-SID gating mechanism that adaptively balances memorization and generalization, and (3) a SID-driven interest alignment module that models the semantic similarity distribution between target items and user histories. SID-Coord can be integrated into existing production ranking systems without modifying the backbone model. Online A/B experiments in a real-world production environment show statistically significant improvements, with a +0.664% gain in long-play rate in search and a +0.369% increase in search playback duration. |
| title | SID-Coord: Coordinating Semantic IDs for ID-based Ranking in Short-Video Search |
| topic | Information Retrieval |
| url | https://arxiv.org/abs/2604.10471 |