WWW / The Web Conference

Enhancing Ride-Hailing Forecasting at DiDi with Multi-View Geospatial Representation Learning from the Web

通过网络多视角地理空间表示学习提升滴滴出行预测

Xixuan Hao, Guicheng Li, Daiqiang Wu, Xusen Guo, Yumeng Zhu, Zhichao Zou, Peng Zhen, Yao Yao, Yuxuan Liang

机构 * The Hong Kong University of Science ； China University of Geoscience (Wuhan) Wuhan China ； Didichuxing Co.\ Ltd Beijing China ； China University of Geoscience (Wuhan) ； Didichuxing Co.\ Ltd 纠错

AI总结 本文提出MVGR-Net框架，通过多视角地理空间表示学习和提示赋能的框架，提升滴滴出行预测的准确性与鲁棒性。

Comments Accepted by The Web Conference 2026

Unifying Deductive and Abductive Reasoning in Knowledge Graphs with Masked Diffusion Model

在知识图谱中统一演绎推理和归纳推理的遮蔽扩散模型

Yisen Gao, Jiaxin Bai, Yi Huang, Xingcheng Fu, Qingyun Sun, Yangqiu Song

机构 * Engineering Hong Kong University of Science ； Engineering \ University Beijing China ； Key Lab of Education Blockchain ； Intelligent Technology \ Normal University Guilin China ； Engineering \ University ； Intelligent Technology \ Normal University 纠错

AI总结 DARK通过统一的遮蔽扩散模型框架，结合自我反思去噪和逻辑探索强化学习，实现了知识图谱中演绎与归纳推理的高效统一。

Comments Accepted by The Web Conference 2026