PreferRec: Learning and Transferring Pareto Preferences for Multi-objective Re-ranking

2026-03-23

AI Summary

Existing multi-objective re-ranking methods overlook users’ Pareto-optimal preferences at the intent level and lack mechanisms for transferring preference knowledge across users. This work proposes a novel approach that explicitly models users’ Pareto preferences at the intent level and introduces a cross-user preference transfer mechanism based on knowledge distillation within a homogeneous optimization space, enabling efficient personalized re-ranking. By doing so, the method not only enhances the trade-off among multiple objectives and improves ranking quality but also significantly reduces redundant learning overhead while preserving personalization.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences
• Search and Optimization: Metareasoning and Metaheuristics

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

Multi-objective re-ranking has become a critical component of modern multi-stage recommender systems, as it tasked to balance multiple conflicting objectives such as accuracy, diversity, and fairness. Existing multi-objective re-ranking methods typically optimize aggregate objectives at the item level using static or handcrafted preference weights. This design overlooks that users inherently exhibit Pareto-optimal preferences at the intent level, reflecting personalized trade-offs among objectives rather than fixed weight combinations. Moreover, most approaches treat re-ranking task for each user as an isolated problem, and repeatedly learn the preferences from scratch. Such a paradigm not only incurs high computational cost, but also ignores the fact that users often share similar preference trade-off structures across objectives. Inspired by the existence of homogeneous multi-objective optimization spaces where Pareto-optimal patterns are transferable, we propose PreferRec, a novel framework that explicitly models and transfers Pareto preferences across users. Specifically, PreferRec is built upon three tightly coupled components: Preference-Aware Pareto Learning aims to capture user intrinsic trade-offs among multiple conflicting objectives at the intent level. By learning Pareto preference representations from re-ranking populations, this component explicitly models how users prioritize different objectives under diverse contexts. Knowledge-Guided Transfer facilitates efficient cross-user knowledge transfer by distilling shared optimization patterns across homogeneous optimization spaces. The transferred knowledge is then used to guide solution selection and personalized re-ranking, biasing the optimization process toward high-quality regions of the Pareto front while preserving user-specific preference characteristics.

Problem

• multi-objective re-ranking
• Pareto preferences
• preference transfer
• recommender systems
• user intent

Innovation

• Pareto preferences
• multi-objective re-ranking
• preference transfer
• intent-level modeling
• knowledge distillation