arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.12385cs.IR
收藏

RankTower:一种增强双塔预排序模型的协同框架

RankTower: A Synergistic Framework for Enhancing Two-Tower Pre-Ranking Model

YaChen Yan, Liubo Li

AI总结:

RankTower提出一种协同双塔预排序框架,通过混合训练目标从级联全阶段学习,在保持解耦推理效率的同时提升排序能力,在公共数据集上显著优于现有模型。

摘要:

在大规模排序系统中,级联架构已被广泛采用,以在效率和有效性之间取得平衡。预排序模块在为后续排序模块选择候选子集方面发挥着至关重要的作用。预排序模型必须在效率和准确性之间保持平衡,以满足在线延迟约束。在本文中,我们提出了一种新颖的神经网络架构,称为RankTower,该架构旨在高效捕获用户-物品交互,同时遵循用户-物品解耦范式以确保在线推理效率。所提出的方法采用了一种混合训练目标,该目标从级联排序系统的全阶段获取的样本中学习,针对不同的样本空间优化不同的目标。该策略旨在增强预排序模型的排序能力,并改善与现有级联排序系统的一致性。在公共数据集上进行的实验结果表明,RankTower显著优于最先进的预排序模型。

英文摘要:

In large-scale ranking systems, cascading architectures have been widely adopted to achieve a balance between efficiency and effectiveness. The pre-ranking module plays a vital role in selecting a subset of candidates for the subsequent ranking module. It is crucial for the pre-ranking model to maintain a balance between efficiency and accuracy to adhere to online latency constraints. In this paper, we propose a novel neural network architecture called RankTower, which is designed to efficiently capture user-item interactions while following the user-item decoupling paradigm to ensure online inference efficiency. The proposed approach employs a hybrid training objective that learns from samples obtained from the full stage of the cascade ranking system, optimizing different objectives for varying sample spaces. This strategy aims to enhance the pre-ranking model's ranking capability and improvement alignment with the existing cascade ranking system. Experimental results conducted on public datasets demonstrate that RankTower significantly outperforms state-of-the-art pre-ranking models.

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。

↑