arXiv cs.AI· Zhi Sheng, Chuyue Wang, Jiahao Ji, Yile Liang, Xuetao Ding, Jinghua Hao, Jie Feng, Yong Li·· 10 小时前AI 评分22
GLIDE:面向动态物流图的可扩展事件感知归纳式预测框架
GLIDE: Scalable and Event-Aware Inductive Forecasting over Evolving Logistics Graphs
AI 导读
GLIDE 是一个面向美团等按需外卖平台的生产级预测框架,用于在规模效应热点(SEH)上预测订单量,支撑实时多对一调度中的订单聚合。它通过图引导的潜在聚合机制,将规模从 10^2 到 10^4 不等的动态物理子图投影到固定大小的语义稳定潜在空间,并适配事件驱动的需求偏移。该工作已被 KDD2027 接收。
正文 · 原文
Abstract:Accurate forecasting of order volume at scale-effect hotspots (SEHs), spatially coherent groups of logistics flows that serve as distributed optimization units for real-time many-to-one dispatch, is a prerequisite for efficient order pooling in on-demand food delivery (OFD) platforms such as Meituan. However, real-world logistics networks present unique challenges that render standard spatiotemporal prediction model ineffective. (i) Dynamic Topology: Unlike static road networks, logistics graphs are ephemeral, with hotspot emerging and vanishing continuously; (ii) Scale--Volume Heterogeneity: Graph sizes vary from $10^2$ to $10^4$, while zero-inflated, long-tailed volumes create computational bottlenecks and bias predictions toward inactivity; and (iii) Event-Driven Disruption: Exogenous events (holidays, weather, academic calendars) induce systematic demand shifts that purely data-driven backbones cannot anticipate. In this paper, we present GLIDE, a production-ready framework that models evolving logistics graphs in a scalable latent space while adapting to heterogeneous demand regimes and event-driven shifts. GLIDE introduces a Graph-Guided Latent Aggregation mechanism, which dynamically projects varying physical subgraphs into a fixed-size, semantically stable latent space via a differentiable sparse assignment...
| Comments: | 14 pages, 5 figures, KDD2027 |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.23942 [cs.AI] |
| (or arXiv:2611.23942v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.23942 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Chuyue Wang [view email]
[v1]
Wed, 18 Nov 2026 06:28:20 UTC (1,651 KB)
来源:arXiv cs.AI · arxiv.org