Modeling Long-term User Behaviors with Diffusion-driven Multi-interest Network for CTR Prediction

2025-08-21

AI Summary

Modeling long-term user behavior for CTR prediction faces challenges including high noise, extremely long behavioral sequences, and difficulty in capturing diverse user interests. To address these, we propose the Diffusion-driven Multi-interest Network (DIMN). DIMN first decouples multi-interest channels via orthogonal decomposition, then explicitly models the latent user interest space through target-guided interest extraction and context-aware diffusion-based generation. Additionally, contrastive learning is incorporated to enhance consistency of interest representations. Operating within a two-stage paradigm, DIMN balances computational efficiency and expressive power while mitigating information loss. Extensive experiments on multiple public and industrial benchmarks demonstrate significant improvements over state-of-the-art methods. Online A/B testing further confirms its practical effectiveness, yielding a 1.52% lift in CTR and a 1.10% increase in CPM.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Data Mining & Knowledge Management: Recommender Systems
• Computer Vision: Diffusion Models for Vision

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Web Mining and Content Analysis: Content-based information diffusion
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

CTR (Click-Through Rate) prediction, crucial for recommender systems and online advertising, etc., has been confirmed to benefit from modeling long-term user behaviors. Nonetheless, the vast number of behaviors and complexity of noise interference pose challenges to prediction efficiency and effectiveness. Recent solutions have evolved from single-stage models to two-stage models. However, current two-stage models often filter out significant information, resulting in an inability to capture diverse user interests and build the complete latent space of user interests. Inspired by multi-interest and generative modeling, we propose DiffuMIN (Diffusion-driven Multi-Interest Network) to model long-term user behaviors and thoroughly explore the user interest space. Specifically, we propose a target-oriented multi-interest extraction method that begins by orthogonally decomposing the target to obtain interest channels. This is followed by modeling the relationships between interest channels and user behaviors to disentangle and extract multiple user interests. We then adopt a diffusion module guided by contextual interests and interest channels, which anchor users' personalized and target-oriented interest types, enabling the generation of augmented interests that align with the latent spaces of user interests, thereby further exploring restricted interest space. Finally, we leverage contrastive learning to ensure that the generated augmented interests align with users' genuine preferences. Extensive offline experiments are conducted on two public datasets and one industrial dataset, yielding results that demonstrate the superiority of DiffuMIN. Moreover, DiffuMIN increased CTR by 1.52% and CPM by 1.10% in online A/B testing. Our source code is available at https://github.com/laiweijiang/DiffuMIN.

Problem

• Modeling long-term user behaviors for CTR prediction
• Overcoming noise and information loss in two-stage models
• Capturing diverse user interests with generative modeling

Innovation

• Target-oriented multi-interest extraction via orthogonal decomposition
• Diffusion module generating augmented interests guided by context
• Contrastive learning aligning generated interests with user preferences