On the Adaptation to Concept Drift for CTR Prediction
Congcong Liu, Yuejiang Li, Fei Teng, Xiwei Zhao, Changping Peng, Zhangang Lin, Jinghe Hu, Jingping Shao
Abstract
Click-through rate (CTR) prediction is a crucial task in web search, recommender systems, and online advertisement displaying. In practical application, CTR models often serve with high-speed user-generated data streams, whose underlying distribution rapidly changing over time. The concept drift problem inevitably exists in those streaming data, which can lead to performance degradation due to the timeliness issue. To ensure model freshness, incremental learning has been widely adopted in real-world production systems. However, it is hard for the incremental update to achieve the balance of the CTR models between the adaptability to capture the fast-changing trends and generalization ability to retain common knowledge. In this paper, we propose adaptive mixture of experts (AdaMoE), a new framework to alleviate the concept drift problem by statistical weighting policy in the data stream of CTR prediction. The extensive offline experiments on both benchmark and a real-world industrial dataset, as well as an online A/B testing show that our AdaMoE significantly outperforms all incremental learning frameworks considered.
Create a lesson
Related papers
NIFT-SQL: Customer-Supervised Table Scoring for Enterprise Text-to-SQL Retrieval
Arjun Rao, Nishant Gopinath
TS-GEAR: Taobao Shangou GEnerative Ad Retrieval
Guofeng Tong, Xu Zhang, Guangliang Yu et al.
CHO-Bench: How Do Context Hints Affect Ad Rankings in LLM Advertising?
Shiqi Zhang, Yang Fei, Xiaokui Xiao
Multi-Modal Agricultural Document Understanding at the DAGRI Task
Zhefan Wang, Da Li, Keping Bi et al.
Proactive Dimension-Adaptive Denoising for Graph Collaborative Filtering via Representation Coherence
Wenjun Li, Dong Zhao, Jiaying Shi et al.
Not All Branches Are Equal: Adaptive Semantic ID Construction for Generative Recommendation
Guy Hadad, Haggai Roitman, Bracha Shapira