用新方法量化用户一致性，解释推荐系统表现差异。
Quantifying User Coherence: A Unified Framework for Analyzing Recommender Systems Across Domains
- 提出两个信息论指标：平均意外度与条件意外度，衡量用户偏好一致性。
- 复杂模型仅在一致用户上表现更好，不一致用户所有模型均表现差。
- 可指导模型优化、分层评估与针对性设计，适合系统开发者使用。
推荐系统在不同用户间的性能差异显著，但原因尚不明确。本文提出统一框架，通过量化用户特征来分析这一差距。引入两个新型信息论度量：平均意外度（S(u)）反映用户对流行物品的偏离程度，与流行度偏差密切相关；平均条件意外度（CS(u)）以领域无关方式衡量用户行为内部一致性。在7种算法、9个数据集上的实验表明，这两个度量是推荐性能的强预测因子。分析发现，复杂模型的性能提升集中在“一致”用户群体，而所有算法在“不一致”用户上表现均不佳。该框架具实际价值：（1）支持稳健的分层评估，识别模型弱点；（2）实现推荐行为与用户偏好的对齐分析；（3）指导针对性系统设计——我们通过仅在‘一致’用户子集上训练专用模型，以更少数据获得更优表现。本研究为理解用户行为提供新视角，并为构建更鲁棒高效的推荐系统提供实用工具。
原文摘要 · Abstract (English)
The performance of Recommender Systems (RS) varies significantly across users, yet the underlying reasons for this variance remain poorly understood. This paper introduces a unified framework to analyze and explain this performance gap by quantifying user profile characteristics. We propose two novel, information-theoretic measures: Mean Surprise (S(u)), which captures a user's deviation from popular items and is closely related to popularity bias, and Mean Conditional Surprise (CS(u)), which measures the internal coherence of a user's interactions in a domain-agnostic manner. Through extensive experiments on 7 algorithms and 9 datasets, we demonstrate that these measures are strong predictors of recommendation performance. Our analysis reveals that performance gains from complex models are concentrated on "coherent" users, while all algorithms perform poorly on "incoherent" users. We show how these measures provide practical utility for the Web community by: (1) enabling robust, stratified evaluation to identify model weaknesses; (2) facilitating a novel analysis of the behavioral alignment of recommendations; and (3) guiding targeted system design, which we validate by training a specialized model on a segment of "coherent" users that achieves superior performance for that group with significantly less data. This work provides a new lens for understanding user behavior and offers practical tools for building more robust and efficient large-scale recommender systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。