Contrastive Curriculum Learning for Sequential User Behavior Modeling via Data Augmentation
Shuqing Bian, Wayne Xin Zhao, Kun Zhou, Jing Cai, Yancheng He, Cunxiang Yin, Ji-Rong Wen · 2021
Within online platforms, it is critical to capture the semantics of sequential user behaviors for accurately modeling user interests. However, dynamic characteristics and sparse behaviors make it difficult to train effective user representations for sequential user behavior modeling.