Enregistré dans:
Détails bibliographiques
Auteurs principaux: Dong, Kuiyao, Lou, Xingyu, Liu, Feng, Wang, Ruian, Yu, Wenyi, Wang, Ping, Wang, Jun
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2411.06826
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866916476934422528
author Dong, Kuiyao
Lou, Xingyu
Liu, Feng
Wang, Ruian
Yu, Wenyi
Wang, Ping
Wang, Jun
author_facet Dong, Kuiyao
Lou, Xingyu
Liu, Feng
Wang, Ruian
Yu, Wenyi
Wang, Ping
Wang, Jun
contents Mixture-of-Experts (MOE) has recently become the de facto standard in Multi-domain recommendation (MDR) due to its powerful expressive ability. However, such MOE-based method typically employs all experts for each instance, leading to scalability issue and low-discriminability between domains and experts. Furthermore, the design of commonly used domain-specific networks exacerbates the scalability issues. To tackle the problems, We propose a novel method named CESAA consists of Conditional Expert Selection (CES) Module and Adaptive Expert Aggregation (AEA) Module to tackle these challenges. Specifically, CES first combines a sparse gating strategy with domain-shared experts. Then AEA utilizes mutual information loss to strengthen the correlations between experts and specific domains, and significantly improve the distinction between experts. As a result, only domain-shared experts and selected domain-specific experts are activated for each instance, striking a balance between computational efficiency and model performance. Experimental results on both public ranking and industrial retrieval datasets verify the effectiveness of our method in MDR tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2411_06826
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Adaptive Conditional Expert Selection Network for Multi-domain Recommendation
Dong, Kuiyao
Lou, Xingyu
Liu, Feng
Wang, Ruian
Yu, Wenyi
Wang, Ping
Wang, Jun
Machine Learning
Information Retrieval
Mixture-of-Experts (MOE) has recently become the de facto standard in Multi-domain recommendation (MDR) due to its powerful expressive ability. However, such MOE-based method typically employs all experts for each instance, leading to scalability issue and low-discriminability between domains and experts. Furthermore, the design of commonly used domain-specific networks exacerbates the scalability issues. To tackle the problems, We propose a novel method named CESAA consists of Conditional Expert Selection (CES) Module and Adaptive Expert Aggregation (AEA) Module to tackle these challenges. Specifically, CES first combines a sparse gating strategy with domain-shared experts. Then AEA utilizes mutual information loss to strengthen the correlations between experts and specific domains, and significantly improve the distinction between experts. As a result, only domain-shared experts and selected domain-specific experts are activated for each instance, striking a balance between computational efficiency and model performance. Experimental results on both public ranking and industrial retrieval datasets verify the effectiveness of our method in MDR tasks.
title Adaptive Conditional Expert Selection Network for Multi-domain Recommendation
topic Machine Learning
Information Retrieval
url https://arxiv.org/abs/2411.06826