DistilledCTR: Accurate and scalable CTR prediction model through model distillation

作者：

Highlights：

• Accurate and scalable CTR prediction model for real-time recommendations.

• Showcase effectiveness of model distillation framework.

• Significance of scalability in real-time recommendations.

摘要

•Accurate and scalable CTR prediction model for real-time recommendations.•Showcase effectiveness of model distillation framework.•Significance of scalability in real-time recommendations.

论文关键词：Recommender Systems,Real-Time Bidding (RTB),Click-Through Rate (CTR),Knowledge Distillation (KD)

论文评审过程：Received 29 August 2021, Revised 28 November 2021, Accepted 26 December 2021, Available online 3 January 2022, Version of Record 22 January 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2021.116474