JointMatch：面向大规模网约车匹配的统一异构图神经求解器
JointMatch: A Unified Heterogeneous Graph Neural Solver for Large-Scale Ride-Sharing Matching
浏览论文内容
中文总结 AI 辅助
针对网约车匹配中请求配对与车辆分配分离导致收入损失和扩展性差的问题，提出统一异构图求解器JointMatch，通过空间稀疏化线性扩展并用GNN一次打分，在纽约出租车数据上超越基线和两阶段方法，速度提升20倍以上。
中文摘要 AI 辅助
网约车平台必须持续决定将哪些开放请求捆绑成共享行程，以及由哪些空闲车辆来服务这些行程。主流学术方法将此问题分解为两个顺序匹配子问题——先进行请求配对，再进行车辆分配——并分别应用独立的求解器。这种分解在计算上方便，但会损失收入且扩展性差，因为第一阶段在可用车辆已知之前就确定了行程捆绑。我们提出JointMatch，一个基于学习的框架，在单一图上同时处理请求配对和车辆分配。该图通过空间邻近性进行稀疏化，使其规模随车辆和请求数量线性增长而非二次增长，并且图神经网络在一次前向传播中为所有候选决策打分。在纽约市黄色出租车数据上，该框架已超过经典的Blossom启发式算法和经过忠实训练的两阶段GNN基线——通常以较大优势——并且在城市规模（车队10000）下，每个调度周期的运行速度比两者快20倍以上。监督训练阶段缩小了大部分剩余的收入差距，而策略梯度微调使训练后的模型与实际收入对齐。
英文摘要
Ride-sharing platforms must continuously decide which open requests to bundle into shared trips and which idle vehicles should serve them. The dominant academic approach decomposes this into two sequential matching problems -- request pairing first, then vehicle assignment -- and applies a separate solver to each. This decomposition is convenient computationally but loses revenue and scales poorly because the first stage commits to ride bundles before the available vehicles are known. We propose JointMatch, a learning-based framework that handles request pairing and vehicle assignment together on a single graph. The graph is sparsified by spatial proximity so that its size grows linearly rather than quadratically with the number of vehicles and requests, and a graph neural network scores all candidate decisions in one forward pass. On the New York City Yellow Taxi data, the framework already exceeds both the classical Blossom heuristic and a faithfully-trained two-stage GNN baseline -- often by a wide margin -- and at city scale (fleet 10000) it runs more than $20\times$ faster per dispatch epoch than either. A supervised training stage closes most of the remaining revenue gap, and a policy-gradient fine-tune aligns the trained model with realised revenue.
