A Unified Search and Recommendation Framework Based on Multi-Scenario Learning for Ranking in E-commerce

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Jinhan, Chen, Qiyu, Xu, Junjie, Li, Junjie, Li, Baoli, Xu, Sulong
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911914032889856
author Liu, Jinhan
Chen, Qiyu
Xu, Junjie
Li, Junjie
Li, Baoli
Xu, Sulong
author_facet Liu, Jinhan
Chen, Qiyu
Xu, Junjie
Li, Junjie
Li, Baoli
Xu, Sulong
contents Search and recommendation (S&R) are the two most important scenarios in e-commerce. The majority of users typically interact with products in S&R scenarios, indicating the need and potential for joint modeling. Traditional multi-scenario models use shared parameters to learn the similarity of multiple tasks, and task-specific parameters to learn the divergence of individual tasks. This coarse-grained modeling approach does not effectively capture the differences between S&R scenarios. Furthermore, this approach does not sufficiently exploit the information across the global label space. These issues can result in the suboptimal performance of multi-scenario models in handling both S&R scenarios. To address these issues, we propose an effective and universal framework for Unified Search and Recommendation (USR), designed with S&R Views User Interest Extractor Layer (IE) and S&R Views Feature Generator Layer (FG) to separately generate user interests and scenario-agnostic feature representations for S&R. Next, we introduce a Global Label Space Multi-Task Layer (GLMT) that uses global labels as supervised signals of auxiliary tasks and jointly models the main task and auxiliary tasks using conditional probability. Extensive experimental evaluations on real-world industrial datasets show that USR can be applied to various multi-scenario models and significantly improve their performance. Online A/B testing also indicates substantial performance gains across multiple metrics. Currently, USR has been successfully deployed in the 7Fresh App.
format Preprint
id arxiv_https___arxiv_org_abs_2405_10835
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Unified Search and Recommendation Framework Based on Multi-Scenario Learning for Ranking in E-commerce
Liu, Jinhan
Chen, Qiyu
Xu, Junjie
Li, Junjie
Li, Baoli
Xu, Sulong
Information Retrieval
Search and recommendation (S&R) are the two most important scenarios in e-commerce. The majority of users typically interact with products in S&R scenarios, indicating the need and potential for joint modeling. Traditional multi-scenario models use shared parameters to learn the similarity of multiple tasks, and task-specific parameters to learn the divergence of individual tasks. This coarse-grained modeling approach does not effectively capture the differences between S&R scenarios. Furthermore, this approach does not sufficiently exploit the information across the global label space. These issues can result in the suboptimal performance of multi-scenario models in handling both S&R scenarios. To address these issues, we propose an effective and universal framework for Unified Search and Recommendation (USR), designed with S&R Views User Interest Extractor Layer (IE) and S&R Views Feature Generator Layer (FG) to separately generate user interests and scenario-agnostic feature representations for S&R. Next, we introduce a Global Label Space Multi-Task Layer (GLMT) that uses global labels as supervised signals of auxiliary tasks and jointly models the main task and auxiliary tasks using conditional probability. Extensive experimental evaluations on real-world industrial datasets show that USR can be applied to various multi-scenario models and significantly improve their performance. Online A/B testing also indicates substantial performance gains across multiple metrics. Currently, USR has been successfully deployed in the 7Fresh App.
title A Unified Search and Recommendation Framework Based on Multi-Scenario Learning for Ranking in E-commerce
topic Information Retrieval
url https://arxiv.org/abs/2405.10835