User Invariant Preference Learning for Multi-Behavior Recommendation

2025-07-20

AI Summary

Existing multi-behavior recommendation methods commonly assume that all user behaviors share a unified preference representation, overlooking the intrinsic coexistence of shared (invariant) and behavior-specific (variant) preferences—where the latter often introduce noise that degrades target-behavior prediction. Method: We propose the User-Invariant Preference Learning (UIPL) framework, the first to incorporate Invariant Risk Minimization (IRM) into multi-behavior recommendation. UIPL constructs heterogeneous behavioral environments based on behavior heterogeneity and integrates a variational autoencoder to explicitly disentangle stable (shared) preferences from dynamic (behavior-specific) ones across behaviors, thereby suppressing noise from non-target behaviors. Contribution/Results: Extensive experiments on four real-world datasets demonstrate that UIPL significantly improves both accuracy and robustness in target-behavior prediction, validating the effectiveness of invariant preference modeling for multi-behavior recommendation.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems

Abstract

In multi-behavior recommendation scenarios, analyzing users' diverse behaviors, such as click, purchase, and rating, enables a more comprehensive understanding of their interests, facilitating personalized and accurate recommendations. A fundamental assumption of multi-behavior recommendation methods is the existence of shared user preferences across behaviors, representing users' intrinsic interests. Based on this assumption, existing approaches aim to integrate information from various behaviors to enrich user representations. However, they often overlook the presence of both commonalities and individualities in users' multi-behavior preferences. These individualities reflect distinct aspects of preferences captured by different behaviors, where certain auxiliary behaviors may introduce noise, hindering the prediction of the target behavior. To address this issue, we propose a user invariant preference learning for multi-behavior recommendation (UIPL for short), aiming to capture users' intrinsic interests (referred to as invariant preferences) from multi-behavior interactions to mitigate the introduction of noise. Specifically, UIPL leverages the paradigm of invariant risk minimization to learn invariant preferences. To implement this, we employ a variational autoencoder (VAE) to extract users' invariant preferences, replacing the standard reconstruction loss with an invariant risk minimization constraint. Additionally, we construct distinct environments by combining multi-behavior data to enhance robustness in learning these preferences. Finally, the learned invariant preferences are used to provide recommendations for the target behavior. Extensive experiments on four real-world datasets demonstrate that UIPL significantly outperforms current state-of-the-art methods.

Problem

• Identify shared user preferences across diverse behaviors
• Mitigate noise from auxiliary behaviors in recommendations
• Learn invariant user preferences using multi-behavior data

Innovation

• Uses invariant risk minimization for preference learning
• Employs variational autoencoder to extract invariant preferences
• Constructs distinct environments from multi-behavior data