Exploiting Behavioral Consistence for Universal User Representation
This work addresses the problem of reducing the need for task-specific model training for developers of personalized services, offering an incremental improvement over existing methods.
This paper tackles the problem of creating universal user representations that can be applied to various downstream applications without modification. The proposed Self-supervised User Modeling Network (SUMN) outperforms state-of-the-art unsupervised methods and is competitive with supervised methods on benchmark datasets.
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.