Bootstrapping Conditional Retrieval for User-to-Item Recommendations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lin, Hongtao, Chen, Haoyu, Jang, Jaewon, Xu, Jiajing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915459452895232
author Lin, Hongtao
Chen, Haoyu
Jang, Jaewon
Xu, Jiajing
author_facet Lin, Hongtao
Chen, Haoyu
Jang, Jaewon
Xu, Jiajing
contents User-to-item retrieval has been an active research area in recommendation system, and two tower models are widely adopted due to model simplicity and serving efficiency. In this work, we focus on a variant called \textit{conditional retrieval}, where we expect retrieved items to be relevant to a condition (e.g. topic). We propose a method that uses the same training data as standard two tower models but incorporates item-side information as conditions in query. This allows us to bootstrap new conditional retrieval use cases and encourages feature interactions between user and condition. Experiments show that our method can retrieve highly relevant items and outperforms standard two tower models with filters on engagement metrics. The proposed model is deployed to power a topic-based notification feed at Pinterest and led to +0.26\% weekly active users.
format Preprint
id arxiv_https___arxiv_org_abs_2508_16793
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Bootstrapping Conditional Retrieval for User-to-Item Recommendations
Lin, Hongtao
Chen, Haoyu
Jang, Jaewon
Xu, Jiajing
Information Retrieval
Machine Learning
User-to-item retrieval has been an active research area in recommendation system, and two tower models are widely adopted due to model simplicity and serving efficiency. In this work, we focus on a variant called \textit{conditional retrieval}, where we expect retrieved items to be relevant to a condition (e.g. topic). We propose a method that uses the same training data as standard two tower models but incorporates item-side information as conditions in query. This allows us to bootstrap new conditional retrieval use cases and encourages feature interactions between user and condition. Experiments show that our method can retrieve highly relevant items and outperforms standard two tower models with filters on engagement metrics. The proposed model is deployed to power a topic-based notification feed at Pinterest and led to +0.26\% weekly active users.
title Bootstrapping Conditional Retrieval for User-to-Item Recommendations
topic Information Retrieval
Machine Learning
url https://arxiv.org/abs/2508.16793