
This paper proposes a Retrieval-Augmented Transformer (RAT) model that enhances fine-grained intra- and cross-sample feature interactions to improve click-through rate prediction.


coremsg

retrieval-augmented-transformer-for-click-through-rate-prediction


Retrieval-Augmented Transformer for Click-Through Rate Prediction


title_rewrite


BAHE, a novel hierarchical encoding approach, decouples the representation extraction of atomic behaviors from the learning of behavior interactions, significantly improving the efficiency and effectiveness of LLM-based CTR prediction with long user sequences.


enhancing-efficiency-and-effectiveness-of-llm-based-click-through-rate-prediction-with-long-textual-user-behaviors


Enhancing Efficiency and Effectiveness of LLM-Based Click-Through Rate Prediction with Long Textual User Behaviors
