Temporal Interest Network for User Response Prediction

Junwei Pan

Abstract:

User behaviors are among the most critical features for user response prediction in recommendation systems.
Many works have revealed that a user's behavior reflects her interest in the candidate item, owing to their semantic or temporal correlation.
While the literature has individually examined each of these correlations, researchers have yet to analyze them in combination, that is, the semantic-temporal correlation.
We empirically measure this correlation and observe intuitive yet robust patterns.
We then examine several popular user interest models and find that, surprisingly, none of them learn such correlation well.

To fill this gap, we propose a Temporal Interest Network (TIN) to capture the semantic-temporal correlation simultaneously between behaviors and the target.
We achieve this by incorporating target-aware temporal encoding, in addition to semantic encoding, to represent behaviors and the target.
Furthermore, we conduct explicit 4-way interaction by deploying target-aware attention and target-aware representation to capture both semantic and temporal correlation.
We conduct comprehensive evaluations on two popular public datasets, and our proposed TIN outperforms the best-performing baselines by 0.43% and 0.29% on GAUC, respectively.
During online A/B testing in Tencent's advertising platform, TIN achieves 1.65% cost lift, and 1.93% GMV lift over the base model.
It has been successfully deployed in production since October 2023, serving the WeChat Moments traffic.
We have released our code at https://github.com/zhouxy1003/TIN.