arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.00368cs.LGcs.IR
收藏

PairRank:通过分治法进行在线成对学习排序

PairRank: Online Pairwise Learning to Rank by Divide-and-Conquer

University of Virginia(弗吉尼亚大学);Walmart Labs(沃尔玛实验室)

Yiling Jia, Huazheng Wang, Stephen Guo, Hongning Wang

摘要:

在线学习排序(OL2R)通过直接优化排名器与用户的交互,消除了显式相关性注释的需要。然而,所需的探索驱使它远离离线学习排序的成功实践,这限制了OL2R的经验性能和实际适用性。在这项工作中,我们提出了估计成对学习排序模型在线。在每一轮中,根据模型对估计的成对排序顺序的置信度对候选文档进行划分和排序,并且仅对不确定的文档对执行探索,即,\emph{divide-and-conquer}。证明了直接定义在错序对数量上的后悔,它将在线解的理论收敛性与其预期的排序性能联系起来。在两个公共学习排序基准数据集上对大量OL2R基线进行比较,证明了所提出的解决方案的有效性。

英文摘要:

Online Learning to Rank (OL2R) eliminates the need of explicit relevance annotation by directly optimizing the rankers from their interactions with users. However, the required exploration drives it away from successful practices in offline learning to rank, which limits OL2R's empirical performance and practical applicability. In this work, we propose to estimate a pairwise learning to rank model online. In each round, candidate documents are partitioned and ranked according to the model's confidence on the estimated pairwise rank order, and exploration is only performed on the uncertain pairs of documents, i.e., \emph{divide-and-conquer}. Regret directly defined on the number of mis-ordered pairs is proven, which connects the online solution's theoretical convergence with its expected ranking performance. Comparisons against an extensive list of OL2R baselines on two public learning to rank benchmark datasets demonstrate the effectiveness of the proposed solution.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑