受大模型启发，用生成式框架提升点击率预测效果。
GRAB: An LLM-Inspired Sequence-First Click-Through Rate Prediction Modeling Paradigm
- 采用序列优先的生成式建模，融合动作感知注意力机制捕捉用户行为动态。
- 线上部署后点击率提升3.49%，收入增长3.05%，且序列越长表现越好。
- 适合关注长序列建模与推荐系统性能提升的工程师和研究者。
传统深度学习推荐模型（DLRMs）在性能与效率上面临瓶颈，普遍存在泛化能力不足与长序列建模困难的问题。受大语言模型（LLM）规模化成功的启发，我们提出百度广告生成排序框架GRAB，一种端到端的点击率（CTR）预测生成式框架。GRAB引入新颖的因果动作感知多通道注意力（CamA）机制，有效捕捉用户行为序列中的时间动态与特定操作信号。全规模线上部署表明，GRAB显著优于现有DLRMs，带来3.05%的收入提升和3.49%的点击率增长。此外，该模型表现出理想的可扩展性：随着交互序列变长，其表达能力呈单调且近似线性提升。
原文摘要 · Abstract (English)
Traditional Deep Learning Recommendation Models (DLRMs) face increasing bottlenecks in performance and efficiency, often struggling with generalization and long-sequence modeling. Inspired by the scaling success of Large Language Models (LLMs), we propose Generative Ranking for Ads at Baidu (GRAB), an end-to-end generative framework for Click-Through Rate (CTR) prediction. GRAB integrates a novel Causal Action-aware Multi-channel Attention (CamA) mechanism to effectively capture temporal dynamics and specific action signals within user behavior sequences. Full-scale online deployment demonstrates that GRAB significantly outperforms established DLRMs, delivering a 3.05% increase in revenue and a 3.49% rise in CTR. Furthermore, the model demonstrates desirable scaling behavior: its expressive power shows a monotonic and approximately linear improvement as longer interaction sequences are utilized.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。