Adaptive Conditional Expert Selection Network for Multi-domain Recommendation

TL;DR

This paper introduces CESAA, a novel multi-domain recommendation method that improves efficiency and discriminability by selectively activating experts using a conditional selection and adaptive aggregation strategy.

Contribution

It proposes CESAA, combining sparse gating and mutual information loss to enhance expert selection and domain distinction in multi-domain recommendation systems.

Findings

CESAA outperforms existing methods on public ranking datasets.

The method reduces computational costs while maintaining high accuracy.

Experimental results validate the effectiveness of the proposed approach.

Abstract

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.