提出YOLOR方法，一步完成推荐列表重排序，解决传统两阶段方法的遗漏问题。
You Only Evaluate Once: A Tree-based Rerank Method at Meituan
- 用树状结构分层提取上下文特征，实现列表级效果提升
- 通过上下文缓存机制实现候选排列间的高效特征复用
- 已在美团外卖平台落地，兼顾准确率与计算效率
重排序在现代推荐系统中至关重要，能捕捉列表内项目间的相互影响。由于组合搜索空间的固有挑战，现有方法普遍采用两阶段范式：简单通用搜索单元（GSU）快速缩小候选范围，精确搜索单元（ESU）则有效选择最优序列。但此类方法在效率与效果间权衡，且存在严重不一致问题——GSU常遗漏被ESU选中的高价值列表。为此，本文提出YOLOR，一种单阶段重排序方法，摒弃GSU仅保留ESU。YOLOR包含：(1) 树状上下文提取模块（TCEM），分层聚合多尺度上下文特征，实现“列表级有效性”；(2) 上下文缓存模块（CCM），支持候选排列间高效特征复用，实现“排列级高效性”。在公开及工业数据集上的大量实验验证了YOLOR性能，该方法已成功部署于美团外卖平台。
原文摘要 · Abstract (English)
Reranking plays a crucial role in modern recommender systems by capturing the mutual influences within the list. Due to the inherent challenges of combinatorial search spaces, most methods adopt a two-stage search paradigm: a simple General Search Unit (GSU) efficiently reduces the candidate space, and an Exact Search Unit (ESU) effectively selects the optimal sequence. These methods essentially involve making trade-offs between effectiveness and efficiency, while suffering from a severe \textbf{inconsistency problem}, that is, the GSU often misses high-value lists from ESU. To address this problem, we propose YOLOR, a one-stage reranking method that removes the GSU while retaining only the ESU. Specifically, YOLOR includes: (1) a Tree-based Context Extraction Module (TCEM) that hierarchically aggregates multi-scale contextual features to achieve "list-level effectiveness", and (2) a Context Cache Module (CCM) that enables efficient feature reuse across candidate permutations to achieve "permutation-level efficiency". Extensive experiments across public and industry datasets validate YOLOR's performance, and we have successfully deployed YOLOR on the Meituan food delivery platform.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。