arXiv：cs.AI· Vladyslav Shevchuk, Carlos Uziel P\'erez Malla, Philipp Wissgott·· 16 小时前
遗传多准则排序与学习排序器在代理偏差和标签污染下的偏差鲁棒性对比
Bias Robustness of Genetic Multi-Criteria Sorting versus Learned Rankers under Proxy Skew and Label Contamination
AI 导读
研究对比免标签的遗传多准则排序（Pikaia 策略变体）与 LightGBM、XGBoost、RankSVM 等 LTR 模型在代理偏差和标签污染下的鲁棒性，测试覆盖 MSLR-WEB10K、Baidu-ULTR、WANDS、Expedia 四个数据集。
正文
Abstract:Learning-to-rank (LTR) models can align rankings with undesignated signals when those signals appear as features or leak into training labels. We compare label-free genetic multi-criteria sorting (open Pikaia strategy variants), which reranks fixed candidate pools using an explicit criteria vector C, to label-trained LTR (LightGBM, XGBoost, RankSVM) under two controlled protocols on MSLR-WEB10K, Baidu-ULTR, WANDS, and Expedia. In the main proxy-skew study, labels remain clean while a calibrated proxy P is available as a feature: Genetic AI rankings show lower Spearman rank-proxy correlation than the LTR peers (e.g. about 0.15-0.16 vs. 0.59-0.87 on WANDS), with both families evaluated jointly on clean nDCG@10 on a bias-utility frontier. In a supporting label-contamination study, training labels are mixed with contaminant B: because Genetic AI methods do not use labels, their bias and utility curves stay flat, whereas LightGBM and XGBoost increase rank-B correlation as contamination rises (OLS bias_slope about 0.58-0.65 on WANDS/Baidu). The results support genetic sorting as an architectural option for optimizing declared attributes on a fixed pool when undesignated proxies or label contaminants must be refused.
| Comments: | 12 pages, 4 figures |
| Subjects: | Neural and Evolutionary Computing (cs.NE); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| ACM classes: | H.3.3; I.2.6 |
| Cite as: | arXiv:2610.14015 [cs.NE] |
| (or arXiv:2610.14015v1 [cs.NE] for this version) | |
| https://doi.org/10.48550/arXiv.2610.14015 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Vladyslav Shevchuk [view email]
[v1]
Tue, 29 Sep 2026 09:14:13 UTC (369 KB)
来源：arXiv：cs.AI · arxiv.org