Exploiting Behavioral Consistence for Universal User Representation

Authors

  • Jie Gu Alibaba Group, Hangzhou, China
  • Feng Wang Alibaba Group, Hangzhou, China
  • Qinghui Sun Alibaba Group, Hangzhou, China
  • Zhiquan Ye Alibaba Group, Hangzhou, China
  • Xiaoxiao Xu Alibaba Group, Hangzhou, China
  • Jingmin Chen Alibaba Group, Hangzhou, China
  • Jun Zhang Alibaba Group, Hangzhou, China

Keywords:

Web Personalization & User Modeling, Information Extraction

Abstract

User modeling is critical for developing personalized services in industry. A common way for user modeling is to learn user representations that can be distinguished by their interests or preferences. In this work, we focus on developing universal user representation model. The obtained universal representations are expected to contain rich information, and be applicable to various downstream applications without further modifications (e.g., user preference prediction and user profiling). Accordingly, we can be free from the heavy work of training task-specific models for every downstream task as in previous works. In specific, we propose Self-supervised User Modeling Network (SUMN) to encode behavior data into the universal representation. It includes two key components. The first one is a new learning objective, which guides the model to fully identify and preserve valuable user information under a self-supervised learning framework. The other one is a multi-hop aggregation layer, which benefits the model capacity in aggregating diverse behaviors. Extensive experiments on benchmark datasets show that our approach can outperform state-of-the-art unsupervised representation methods, and even compete with supervised ones.

Downloads

Published

2021-05-18

How to Cite

Gu, J., Wang, F., Sun, Q., Ye, Z., Xu, X., Chen, J., & Zhang, J. (2021). Exploiting Behavioral Consistence for Universal User Representation. Proceedings of the AAAI Conference on Artificial Intelligence, 35(5), 4063-4071. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16527

Issue

Section

AAAI Technical Track on Data Mining and Knowledge Management