Learning Transferrable Parameters for Long-tailed Sequential User Behavior Modeling
This work addresses the long-tailed distribution issue in sequential user behavior modeling for online services like e-commerce and advertising, offering a solution that is incremental but directly adaptable to existing models.
The paper tackles the problem of long-tailed user behavior distributions in sequential modeling, which is often overlooked, by proposing a framework that learns transferable parameters to improve performance for tail users, achieving superior results on four real-world datasets compared to state-of-the-art baselines.
Sequential user behavior modeling plays a crucial role in online user-oriented services, such as product purchasing, news feed consumption, and online advertising. The performance of sequential modeling heavily depends on the scale and quality of historical behaviors. However, the number of user behaviors inherently follows a long-tailed distribution, which has been seldom explored. In this work, we argue that focusing on tail users could bring more benefits and address the long tails issue by learning transferrable parameters from both optimization and feature perspectives. Specifically, we propose a gradient alignment optimizer and adopt an adversarial training scheme to facilitate knowledge transfer from the head to the tail. Such methods can also deal with the cold-start problem of new users. Moreover, it could be directly adaptive to various well-established sequential models. Extensive experiments on four real-world datasets verify the superiority of our framework compared with the state-of-the-art baselines.