Precise user modeling is critical for online personalized recommendation services. Generally, users' interests are diverse and are not limited to a single aspect, which is particularly evident when their behaviors are observed for a longer time. For example, a user may demonstrate interests in cats/dogs, dancing and food \& delights when browsing short videos on Tik Tok; the same user may show interests in real estate and women's wear in her web browsing behaviors. Traditional models tend to encode a user's behaviors into a single embedding vector, which do not have enough capacity to effectively capture her diverse interests. This paper proposes a Sequential User Matrix (SUM) to accurately and efficiently capture users' diverse interests. SUM models user behavior with a multi-channel network, with each channel representing a different aspect of the user's interests. User states in different channels are updated by an \emph{erase-and-add} paradigm with interest- and instance-level attention. We further propose a local proximity debuff component and a highway connection component to make the model more robust and accurate. SUM can be maintained and updated incrementally, making it feasible to be deployed for large-scale online serving. We conduct extensive experiments on two datasets. Results demonstrate that SUM consistently outperforms state-of-the-art baselines.
@article{arxiv.2102.09211,
title = {Multi-Interest-Aware User Modeling for Large-Scale Sequential Recommendations},
author = {Jianxun Lian and Iyad Batal and Zheng Liu and Akshay Soni and Eun Yong Kang and Yajun Wang and Xing Xie},
journal= {arXiv preprint arXiv:2102.09211},
year = {2021}
}