PTUM: Pre-training User Model from Unlabeled User Behaviors via Self-supervision
This addresses the challenge of limited labeled data in personalized web services, offering a novel approach but is incremental in applying self-supervised pre-training to user behavior data.
The paper tackles the problem of user modeling with scarce labeled data by proposing a pre-training method for user models using large-scale unlabeled behavior data, achieving validated effectiveness on two real-world datasets.
User modeling is critical for many personalized web services. Many existing methods model users based on their behaviors and the labeled data of target tasks. However, these methods cannot exploit useful information in unlabeled user behavior data, and their performance may be not optimal when labeled data is scarce. Motivated by pre-trained language models which are pre-trained on large-scale unlabeled corpus to empower many downstream tasks, in this paper we propose to pre-train user models from large-scale unlabeled user behaviors data. We propose two self-supervision tasks for user model pre-training. The first one is masked behavior prediction, which can model the relatedness between historical behaviors. The second one is next $K$ behavior prediction, which can model the relatedness between past and future behaviors. The pre-trained user models are finetuned in downstream tasks to learn task-specific user representations. Experimental results on two real-world datasets validate the effectiveness of our proposed user model pre-training method.