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.

翻译：在大规模排序系统中，级联架构已被广泛采用，以实现效率与效果之间的平衡。预排序模块在筛选候选子集以供后续排序模块处理方面起着至关重要的作用。预排序模型必须在效率与准确性之间保持平衡，以满足在线延迟约束，这一点至关重要。本文提出了一种名为RankTower的新型神经网络架构，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。所提出的方法采用混合训练目标，从级联排序系统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。该策略旨在提升预排序模型的排序能力，并增强其与现有级联排序系统的改进一致性。在公开数据集上进行的实验结果表明，RankTower显著优于当前最先进的预排序模型。