Regularized Adversarial Sampling and Deep Time-aware Attention for Click-Through Rate Prediction
This work addresses CTR prediction for online advertising systems, offering incremental improvements by integrating temporal modeling and better sampling techniques.
The paper tackles improving click-through rate (CTR) prediction by proposing a time-aware attention model that uses absolute and relative temporal signals to capture user behaviors, and a regularized adversarial sampling strategy to address data imbalance and enhance training efficiency. Experiments on real-world datasets show significant improvements, though specific numbers are not provided in the abstract.
Improving the performance of click-through rate (CTR) prediction remains one of the core tasks in online advertising systems. With the rise of deep learning, CTR prediction models with deep networks remarkably enhance model capacities. In deep CTR models, exploiting users' historical data is essential for learning users' behaviors and interests. As existing CTR prediction works neglect the importance of the temporal signals when embed users' historical clicking records, we propose a time-aware attention model which explicitly uses absolute temporal signals for expressing the users' periodic behaviors and relative temporal signals for expressing the temporal relation between items. Besides, we propose a regularized adversarial sampling strategy for negative sampling which eases the classification imbalance of CTR data and can make use of the strong guidance provided by the observed negative CTR samples. The adversarial sampling strategy significantly improves the training efficiency, and can be co-trained with the time-aware attention model seamlessly. Experiments are conducted on real-world CTR datasets from both in-station and out-station advertising places.