提出轻量级方法Linear-PAL，解决电商排序中的位置偏差问题。
Linear-PAL: A Lightweight Ranker for Mitigating Shortcut Learning in Personalized, High-Bias Tabular Ranking
- 通过结构约束和正则化抑制深度模型的捷径学习
- 在420万数据上实现0.7626的去偏相关性AUC，训练快43倍
- 适合需要高频重训练的个性化实时推荐场景
在电商排序中，用户隐式反馈受位置偏差严重影响——用户更倾向于点击排名靠前的项目，而非其相关性。尽管深度学习模型（如双塔网络）是主流去偏方法，我们发现，在高偏差环境下，最先进的深度集成模型会因过拟合排名信号而产生捷径学习，导致排序质量下降，尽管预测准确率很高。为此，我们提出轻量级框架Linear-PAL，通过显式特征组合与强正则化实现去偏。同时引入向量化整数哈希技术，将字符串操作替换为O(N)的向量化运算。在包含420万样本的大规模数据集上，Linear-PAL实现了帕累托占优：去偏排序质量（相关性AUC：0.7626 vs. 0.6736）优于深度集成模型，且训练延迟降低43倍（40秒 vs. 1762秒）。该效率支持高频重训练，使系统能捕捉用户特定的新兴市场趋势，实现实时个性化排序。
原文摘要 · Abstract (English)
In e-commerce ranking, implicit user feedback is systematically confounded by Position Bias -- the strong propensity of users to interact with top-ranked items regardless of relevance. While Deep Learning architectures (e.g., Two-Tower Networks) are the standard solution for de-biasing, we demonstrate that in High-Bias Regimes, state-of-the-art Deep Ensembles suffer from Shortcut Learning: they minimize training loss by overfitting to the rank signal, leading to degraded ranking quality despite high prediction accuracy. We propose Linear Position-bias Aware Learning (Linear-PAL), a lightweight framework that enforces de-biasing through structural constraints: explicit feature conjunctions and aggressive regularization. We further introduce a Vectorized Integer Hashing technique for feature generation, replacing string-based operations with $O(N)$ vectorized arithmetic. Evaluating on a large-scale dataset (4.2M samples), Linear-PAL achieves Pareto Dominance: it outperforms Deep Ensembles in de-biased ranking quality (Relevance AUC: 0.7626 vs. 0.6736) while reducing training latency by 43x (40s vs 1762s). This computational efficiency enables high-frequency retraining, allowing the system to capture user-specific emerging market trends and deliver robust, personalized ranking in near real-time.
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。