论文标题
APG：单击率预测的自适应参数生成网络
APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction
论文作者
论文摘要
在许多Web应用程序中，基于深度学习的CTR预测模型（简短的CTR模型）被广泛采用。传统的深入CTR模型以静态方式学习模式，即网络参数在所有实例中都是相同的。但是，这种方式几乎无法表征每个可能具有不同基础分布的实例。它实际上限制了深CTR模型的表示功能，从而导致了次优的结果。在本文中，我们提出了一个高效，有效和通用的模块，称为自适应参数生成网络（APG），该模块可以根据不同的实例动态地为深层CTR模型生成参数。广泛的实验评估结果表明，APG可以应用于各种深层CTR模型，并显着提高其性能。同时，与常规的Deep CTR模型相比，APG可以将时间成本降低38.7 \％，并且记忆使用率减少96.6 \％。我们已经在工业赞助的搜索系统中部署了APG，并分别获得了3 \％CTR增益和1 \％RPM增益。
In many web applications, deep learning-based CTR prediction models (deep CTR models for short) are widely adopted. Traditional deep CTR models learn patterns in a static manner, i.e., the network parameters are the same across all the instances. However, such a manner can hardly characterize each of the instances which may have different underlying distributions. It actually limits the representation power of deep CTR models, leading to sub-optimal results. In this paper, we propose an efficient, effective, and universal module, named as Adaptive Parameter Generation network (APG), which can dynamically generate parameters for deep CTR models on-the-fly based on different instances. Extensive experimental evaluation results show that APG can be applied to a variety of deep CTR models and significantly improve their performance. Meanwhile, APG can reduce the time cost by 38.7\% and memory usage by 96.6\% compared to a regular deep CTR model. We have deployed APG in the industrial sponsored search system and achieved 3\% CTR gain and 1\% RPM gain respectively.
