Generative Long-term User Interest Modeling for Click-Through Rate Prediction

2026-05-15

AI Summary

Existing approaches to long-term user interest modeling rely on target items during the retrieval phase to filter historical behaviors, which often overlooks latent interests, introduces bias, and incurs high computational costs, hindering online deployment. To address these limitations, this work proposes GenLI, the first model to incorporate a generative mechanism for capturing multidimensional user interest distributions in a target-agnostic manner. GenLI integrates an Interest Generation Module (IGM), a lookup-based Behavior Retrieval Module (BRM), and a fine-grained gated Interest Fusion Module (IFM) to effectively encode inter-behavior interactions while reducing behavior weighting complexity to O(1). Experimental results demonstrate that GenLI significantly improves CTR prediction accuracy and substantially reduces online inference latency, achieving an effective balance between interest diversity and system efficiency.

Abstract

Modeling long-term user interests with massive historical user behaviors enhances click-through rate (CTR) prediction performance in advertising and recommendation systems. Typically, a two-stage framework is widely adopted, where a general search unit (GSU) first retrieves top-$k$ relevant behaviors towards the target item, and an exact search unit (ESU) generates interest features via tailored attention. However, current target-centered GSU would ignore other latent user interests, leading to incomplete and biased interest features. Additionally, the matching-based retrieval process in GSUs depends on the pairwise similarity score between target item and each historical behavior, which not only becomes time-consuming for online services as user behaviors continue to grow, but also overlooks the interaction information among user behaviors. To combat these problems, we propose a \textbf{Gen}erative \textbf{L}ong-term user \textbf{I}nterest model named GenLI for CTR prediction. GenLI consists of an interest generation module (IGM), a behavior retrieval module (BRM), and an interest fusion module (IFM). The IGM generates multiple interest distributions to indicate different aspects of real-time user interests, which is target-independent and incorporates interaction information among behaviors, ensuring complete and diverse interest features. The BRM selects related behaviors via a simple lookup operation, reducing the time complexity for weighting each behavior to $O(1)$. Finally, the IFM uses delicate gating mechanisms to generate interest features. Based on the generation process, GenLI improves the diversity of user interests and avoids complex matching-based behavioral retrieval, achieving a better balance between accuracy and efficiency for CTR prediction.

Problem

• long-term user interest
• click-through rate prediction
• behavior retrieval
• interest modeling
• user behavior interaction

Innovation

• Generative Interest Modeling
• Long-term User Interest
• CTR Prediction
• Efficient Retrieval
• Behavior Interaction