MAC：首个提供多归因机制标签的 CVR 预测基准发布
MAC: A Conversion Rate Prediction Benchmark Featuring Labels Under Multiple Attribution Mechanisms
研究团队发布 MAC，首个包含多种归因机制转化标签的公开 CVR 预测数据集，并开源覆盖多种基线方法的 PyMAL 库。实验显示多归因学习在不同归因设置下均带来稳定性能提升，尤其利好转化路径长的用户；但预测首次点击转化目标时，简单增加辅助目标反而有害。基于此提出的 MoAE 方法在 MAC 上显著超越现有 SOTA 多归因学习方法。
Authors:Jinqi Wu, Sishuo Chen, Zhangming Chan, Yong Bai, Lei Zhang, Sheng Chen, Chenghuan Hou, Xiang-Rong Sheng, Han Zhu, Jian Xu, Bo Zheng, Chaoyou Fu
Abstract:Multi-attribution learning (MAL), which enhances model performance by learning from conversion labels yielded by multiple attribution mechanisms, has emerged as a promising learning paradigm for conversion rate (CVR) prediction. However, the conversion labels in public CVR datasets are generated by a single attribution mechanism, hindering the development of MAL approaches.
To address this data gap, we establish the Multi-Attribution Benchmark (MAC), the first public CVR dataset featuring labels from multiple attribution mechanisms. Besides, to promote reproducible research on MAL, we develop PyMAL, an open-source library covering a wide array of baseline methods. We conduct comprehensive experimental analyses on MAC and reveal three key insights: (1) MAL brings consistent performance gains across different attribution settings, especially for users featuring long conversion paths. (2) The performance growth scales up with objective complexity in most settings; however, when predicting first-click conversion targets, simply adding auxiliary objectives is counterproductive, underscoring the necessity of careful selection of auxiliary objectives. (3) Two architectural design principles are paramount: first, to fully learn the multi-attribution knowledge, and second, to fully leverage this knowledge to serve the main task. Motivated by these findings, we propose Mixture of Asymmetric Experts (MoAE), an effective MAL approach incorporating multi-attribution knowledge learning and main task-centric knowledge utilization. Experiments on MAC show that MoAE substantially surpasses the existing state-of-the-art MAL method. We believe that our benchmark and insights will foster future research in the MAL field. Our MAC benchmark and the PyMAL algorithm library are publicly available at this https URL.
| Comments: | 11 pages, 5 figures. Updated to the camera-ready version published in the proceedings of KDD 2026. Code and data available at this https URL |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2603.02184 [cs.LG] |
| (or arXiv:2603.02184v3 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2603.02184 arXiv-issued DOI via DataCite |
|
| Journal reference: | Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2 (KDD '26), pp. 10009-10019, 2026 |
| Related DOI: | https://doi.org/10.1145/3770855.3817488
DOI(s) linking to related resources |
Submission history
From: Jinqi Wu [view email]
[v1]
Mon, 2 Mar 2026 18:51:01 UTC (599 KB)
[v2]
Fri, 7 Aug 2026 03:38:17 UTC (698 KB)
[v3]
Thu, 12 Nov 2026 05:53:30 UTC (693 KB)
来源：arXiv cs.AI · arxiv.org