Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Ruochen Yang, Xiaodong Li, Jiawei Sheng, Jiangxia Cao, Xinkui Lin, Shen Wang, Shuang Yang, Zhaojie Liu, Tingwen Liu

TL;DR

A Multi-Behavior AutoEncoder (MBAE) is designed to construct a unified user latent preference space, facilitating interaction and collaboration across Behaviors, within Behavior-aware RoPE (BaRoPE) employed for multiple information fusion.

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.

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

TL;DR

A Multi-Behavior AutoEncoder (MBAE) is designed to construct a unified user latent preference space, facilitating interaction and collaboration across Behaviors, within Behavior-aware RoPE (BaRoPE) employed for multiple information fusion.

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.
Paper Structure (39 sections, 30 equations, 10 figures, 4 tables, 2 algorithms)

This paper contains 39 sections, 30 equations, 10 figures, 4 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Preliminary
  3. Problem Formulation
  4. Diffusion Model
  5. Methodology
  6. Multi-Behavior AutoEncoder
  7. Latent Preference Diffusion
  8. Multi-Condition Guided Layer Norm
  9. Training and Inference
  10. Experiments
  11. Experimental Settings
  12. Dataset.
  13. Evaluation Metrics.
  14. Baselines.
  15. Parameters Settings.
  16. ...and 24 more sections

Figures (10)

  • Figure 1: Motivation of our work. Discriminative paradigm is constrained by candidate set and interaction history, while generative paradigm incorporating user's latent preference achieves accuracy and diversity.
  • Figure 2: The overall framework of our model. Stage 1 trains MBAE to construct the latent space for unifying preferences. Stage 2 achieves the transfer from behavior-agnostic to behavior-specific in the latent space based on DM.
  • Figure 3: The architecture of BaRoPE.
  • Figure 4: The architecture of MCGLN. The behavior-agnostic preference $z_{\varnothing}$ serves as the transfer subject. The target behavior $b_t$ guides the direction as hard router for MoE. Condition representation $e_b$ and $e_t$ generate adaptive weights.
  • Figure 5: The comparison of attention matrics of APE and BaRoPE on user_1 in Retail dataset. The sequential arrangement of Item_Behavior means the user interacted with item through behavior.
  • ...and 5 more figures