RankList - A Listwise Preference Learning Framework for Predicting Subjective Preferences

2025-08-13

AI Summary

Existing preference learning methods (e.g., RankNet) model only local pairwise comparisons, failing to ensure global ranking consistency—especially in subjective judgment tasks. To address this, we propose RankList, the first preference learning framework designed for list-level supervision. It probabilistically models both local and non-local ordering constraints to explicitly enhance global consistency. Key contributions include: (i) generalizing RankNet to structured list inputs; (ii) introducing a skip-wise comparison mechanism to better capture long-range ordinal dependencies; and (iii) adopting a log-sum-exp approximation to improve training efficiency and ranking fidelity. Evaluated on multiple benchmarks in speech emotion and image aesthetics, RankList achieves significant gains in Kendall’s Tau and ranking accuracy over strong baselines, while demonstrating superior cross-domain generalization capability.

Technology Category

• Machine Learning: Learning Preferences or Rankings
• Knowledge Representation and Reasoning: Preferences
• Natural Language Processing: Learning & Optimization for NLP

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs

Abstract

Preference learning has gained significant attention in tasks involving subjective human judgments, such as emph{speech emotion recognition} (SER) and image aesthetic assessment. While pairwise frameworks such as RankNet offer robust modeling of relative preferences, they are inherently limited to local comparisons and struggle to capture global ranking consistency. To address these limitations, we propose RankList, a novel listwise preference learning framework that generalizes RankNet to structured list-level supervision. Our formulation explicitly models local and non-local ranking constraints within a probabilistic framework. The paper introduces a log-sum-exp approximation to improve training efficiency. We further extend RankList with skip-wise comparisons, enabling progressive exposure to complex list structures and enhancing global ranking fidelity. Extensive experiments demonstrate the superiority of our method across diverse modalities. On benchmark SER datasets (MSP-Podcast, IEMOCAP, BIIC Podcast), RankList achieves consistent improvements in Kendall's Tau and ranking accuracy compared to standard listwise baselines. We also validate our approach on aesthetic image ranking using the Artistic Image Aesthetics dataset, highlighting its broad applicability. Through ablation and cross-domain studies, we show that RankList not only improves in-domain ranking but also generalizes better across datasets. Our framework offers a unified, extensible approach for modeling ordered preferences in subjective learning scenarios.

Problem

• Develops listwise framework for subjective preference learning tasks
• Addresses limitations of pairwise comparisons in ranking consistency
• Improves global ranking accuracy across diverse modalities like SER

Innovation

• Listwise preference learning framework
• Log-sum-exp approximation for efficiency
• Skip-wise comparisons enhance ranking fidelity