Dynamic Parameterized Network for CTR Prediction
This addresses the challenge of efficient and effective feature interaction modeling for CTR prediction in recommendation systems, with incremental improvements over existing methods.
The paper tackles the problem of capturing feature relations in click-through rate (CTR) prediction by proposing a Dynamic Parameterized Operation (DPO) to learn explicit and implicit interactions instance-wisely, resulting in significant outperformance over state-of-the-art methods in offline and online tests, with deployment in a major e-commerce ranking system.
Learning to capture feature relations effectively and efficiently is essential in click-through rate (CTR) prediction of modern recommendation systems. Most existing CTR prediction methods model such relations either through tedious manually-designed low-order interactions or through inflexible and inefficient high-order interactions, which both require extra DNN modules for implicit interaction modeling. In this paper, we proposed a novel plug-in operation, Dynamic Parameterized Operation (DPO), to learn both explicit and implicit interaction instance-wisely. We showed that the introduction of DPO into DNN modules and Attention modules can respectively benefit two main tasks in CTR prediction, enhancing the adaptiveness of feature-based modeling and improving user behavior modeling with the instance-wise locality. Our Dynamic Parameterized Networks significantly outperforms state-of-the-art methods in the offline experiments on the public dataset and real-world production dataset, together with an online A/B test. Furthermore, the proposed Dynamic Parameterized Networks has been deployed in the ranking system of one of the world's largest e-commerce companies, serving the main traffic of hundreds of millions of active users.