Regularized Adversarial Sampling and Deep Time-aware Attention for Click-Through Rate Prediction

TL;DR

This paper introduces a novel deep learning framework for CTR prediction that incorporates time-aware attention mechanisms and a regularized adversarial sampling strategy to better model temporal user behaviors and improve training efficiency.

Contribution

It proposes a time-aware attention model utilizing absolute and relative temporal signals, and a regularized adversarial negative sampling method for enhanced CTR prediction.

Findings

Time-aware attention improves modeling of user behavior.

Adversarial sampling enhances training efficiency.

Model achieves better performance on real-world datasets.

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.