Large Memory Network for Recommendation

TL;DR

This paper introduces Large Memory Network (LMN), a scalable model that enhances user behavior sequence modeling in recommender systems by storing extensive user history in a large memory, improving recommendation accuracy and deployment efficiency.

Contribution

The paper proposes LMN, a novel large-scale memory-based approach for sequential recommendation that effectively captures long-term user interests and is scalable for industrial deployment.

Findings

LMN outperforms existing models in offline experiments.

Memory scaling experiments show effective handling of million-scale data.

Online A/B tests demonstrate improved recommendation performance in Douyin ECS.

Abstract

Modeling user behavior sequences in recommender systems is essential for understanding user preferences over time, enabling personalized and accurate recommendations for improving user retention and enhancing business values. Despite its significance, there are two challenges for current sequential modeling approaches. From the spatial dimension, it is difficult to mutually perceive similar users' interests for a generalized intention understanding; from the temporal dimension, current methods are generally prone to forgetting long-term interests due to the fixed-length input sequence. In this paper, we present Large Memory Network (LMN), providing a novel idea by compressing and storing user history behavior information in a large-scale memory block. With the elaborated online deployment strategy, the memory block can be easily scaled up to million-scale in the industry. Extensive offline comparison experiments, memory scaling up experiments, and online A/B test on Douyin E-Commerce Search (ECS) are performed, validating the superior performance of LMN. Currently, LMN has been fully deployed in Douyin ECS, serving millions of users each day.