From Agnostic to Specific: Latent Preference Diffusion for Multi-Behavior Sequential Recommendation

2026-02-26

AI Summary

Existing methods struggle to model the uncertainty in user transitions from low-entropy behaviors to high-entropy items and often overlook latent preferences, thereby limiting the performance of multi-behavior sequential recommendation. To address this, this work proposes FatsMB, a novel framework that introduces diffusion mechanisms into multi-behavior recommendation for the first time, enabling the generation of behavior-specific preferences from behavior-agnostic representations within a unified implicit preference space. FatsMB integrates key components including a Multi-Behavior Autoencoder (MBAE), Behavior-aware Rotary Position Embedding (BaRoPE), and Multi-Condition Guided Layer Normalization (MCGLN) to effectively transfer and fuse multi-behavior information. Extensive experiments demonstrate that FatsMB significantly improves both accuracy and diversity of recommendations across multiple real-world datasets.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Multiagent Learning

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Multi-behavior sequential recommendation (MBSR) aims to learn the dynamic and heterogeneous interactions of users' multi-behavior sequences, so as to capture user preferences under target behavior for the next interacted item prediction. Unlike previous methods that adopt unidirectional modeling by mapping auxiliary behaviors to target behavior, recent concerns are shifting from behavior-fixed to behavior-specific recommendation. However, these methods still ignore the user's latent preference that underlying decision-making, leading to suboptimal solutions. Meanwhile, due to the asymmetric deterministic between items and behaviors, discriminative paradigm based on preference scoring is unsuitable to capture the uncertainty from low-entropy behaviors to high-entropy items, failing to provide efficient and diverse recommendation. To address these challenges, we propose \textbf{FatsMB}, a framework based diffusion model that guides preference generation \textit{\textbf{F}rom Behavior-\textbf{A}gnostic \textbf{T}o Behavior-\textbf{S}pecific} in latent spaces, enabling diverse and accurate \textit{\textbf{M}ulti-\textbf{B}ehavior Sequential Recommendation}. Specifically, we design a Multi-Behavior AutoEncoder (MBAE) to construct a unified user latent preference space, facilitating interaction and collaboration across Behaviors, within Behavior-aware RoPE (BaRoPE) employed for multiple information fusion. Subsequently, we conduct target behavior-specific preference transfer in the latent space, enriching with informative priors. A Multi-Condition Guided Layer Normalization (MCGLN) is introduced for the denoising. Extensive experiments on real-world datasets demonstrate the effectiveness of our model.

Problem

• Multi-behavior Sequential Recommendation
• Latent Preference
• Behavior-specific Recommendation
• Uncertainty Modeling
• Preference Generation

Innovation

• Latent Preference Diffusion
• Multi-Behavior Sequential Recommendation
• Behavior-Specific Modeling
• Diffusion Model
• Multi-Condition Guided Layer Normalization