Adaptive Domain Scaling for Personalized Sequential Modeling in Recommenders

Zheng Chai, Hui Lu, Di Chen, Qin Ren, Yuchao Zheng, Xun Zhou

Abstract: Users generally exhibit complex behavioral patterns and diverse intentions in multiple business scenarios of super APPs, presenting great challenges to industrial multi-domain recommenders. Current researches and practices generally emphasize sophisticated network structures to accommodate diverse data distributions, while neglecting the inherent understanding of user behavioral sequence from the multi-domain perspective. In this paper, we present Adaptive Domain Scaling (ADS) model, which comprehensively enhances the personalization capability in target-aware sequence modeling across multiple domains. Specifically, ADS comprises of two major modules, including personalized sequence representation generation (PSRG) and personalized candidate representation generation (PCRG). The modules contribute to the tailored multi-domain modeling by dynamically learning both the user interacted item representation and the candidate target item representation, facilitating adaptive user intention understanding. Experiments on both a public and two billion-scaled industrial datasets, and online A/B tests on two influential business scenarios at ByteDance validate its effectiveness. Currently, ADS has been fully deployed in dozens of recommendation services at ByteDance, serving billions of users.