InteractRank: Personalized Web-Scale Search Pre-Ranking with Cross Interaction Features
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_ | 1866913784892751872 |
|---|---|
| author | Khandagale, Sujay Juneja, Bhawna Agarwal, Prabhat Subramanian, Aditya Yang, Jaewon Wang, Yuting |
| author_facet | Khandagale, Sujay Juneja, Bhawna Agarwal, Prabhat Subramanian, Aditya Yang, Jaewon Wang, Yuting |
| contents | Modern search systems use a multi-stage architecture to deliver personalized results efficiently. Key stages include retrieval, pre-ranking, full ranking, and blending, which refine billions of items to top selections. The pre-ranking stage, vital for scoring and filtering hundreds of thousands of items down to a few thousand, typically relies on two tower models due to their computational efficiency, despite often lacking in capturing complex interactions. While query-item cross interaction features are paramount for full ranking, integrating them into pre-ranking models presents efficiency-related challenges. In this paper, we introduce InteractRank, a novel two tower pre-ranking model with robust cross interaction features used at Pinterest. By incorporating historical user engagement-based query-item interactions in the scoring function along with the two tower dot product, InteractRank significantly boosts pre-ranking performance with minimal latency and computation costs. In real-world A/B experiments at Pinterest, InteractRank improves the online engagement metric by 6.5% over a BM25 baseline and by 3.7% over a vanilla two tower baseline. We also highlight other components of InteractRank, like real-time user-sequence modeling, and analyze their contributions through offline ablation studies. The code for InteractRank is available at https://github.com/pinterest/atg-research/tree/main/InteractRank. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_06609 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | InteractRank: Personalized Web-Scale Search Pre-Ranking with Cross Interaction Features Khandagale, Sujay Juneja, Bhawna Agarwal, Prabhat Subramanian, Aditya Yang, Jaewon Wang, Yuting Information Retrieval Artificial Intelligence Machine Learning H.3.3 Modern search systems use a multi-stage architecture to deliver personalized results efficiently. Key stages include retrieval, pre-ranking, full ranking, and blending, which refine billions of items to top selections. The pre-ranking stage, vital for scoring and filtering hundreds of thousands of items down to a few thousand, typically relies on two tower models due to their computational efficiency, despite often lacking in capturing complex interactions. While query-item cross interaction features are paramount for full ranking, integrating them into pre-ranking models presents efficiency-related challenges. In this paper, we introduce InteractRank, a novel two tower pre-ranking model with robust cross interaction features used at Pinterest. By incorporating historical user engagement-based query-item interactions in the scoring function along with the two tower dot product, InteractRank significantly boosts pre-ranking performance with minimal latency and computation costs. In real-world A/B experiments at Pinterest, InteractRank improves the online engagement metric by 6.5% over a BM25 baseline and by 3.7% over a vanilla two tower baseline. We also highlight other components of InteractRank, like real-time user-sequence modeling, and analyze their contributions through offline ablation studies. The code for InteractRank is available at https://github.com/pinterest/atg-research/tree/main/InteractRank. |
| title | InteractRank: Personalized Web-Scale Search Pre-Ranking with Cross Interaction Features |
| topic | Information Retrieval Artificial Intelligence Machine Learning H.3.3 |
| url | https://arxiv.org/abs/2504.06609 |