KDD 2025 | (8月轮)时空数据(Spatial-temporal)论文总结

KDD 2025将在2025年8月3号到7号在加拿大多伦多举行，本文总结了KDD 2025(August Cycle)有关时空数据（Spatial-Temporal）相关文章，共计17篇，其中1-12为Research Track，13-17为ADS Track。

时空数据Topic：时空预测，轨迹表示学习，轨迹生成，轨迹模拟，信控优化等。如有疏漏，欢迎补充！

🌟【紧跟前沿】“时空探索之旅”与你一起探索时空奥秘！🚀
欢迎大家关注时空探索之旅时空探索之旅

Research Track

1 Dynamic Localisation of Spatial-Temporal Graph Neural Network

链接：https://dl.acm.org/doi/10.1145/3690624.3709331

作者：Wenying Duan, Shujun Guo, Zimu Zhou, Wei Huang, Hong Rao, Xiaoxi He

关键词：动态时空图神经网络

2 Efficient Large-Scale Traffic Forecasting with Transformers: A Spatial Data Management Perspective

链接：https://dl.acm.org/doi/10.1145/3690624.3709177

代码：https://github.com/LMissher/PatchSTG

作者：Yuchen Fang, Yuxuan Liang, Bo Hui, Zezhi Shao, Liwei Deng, Xu Liu, Xinke Jiang, Kai Zheng

关键词：交通预测，空间管理

3 AutoSTF: Decoupled Neural Architecture Search for Cost-Effective Automated Spatio-Temporal Forecasting

链接：https://dl.acm.org/doi/10.1145/3690624.3709323

代码：https://github.com/usail-hkust/AutoSTF

作者： Tengfei Lyu, Weijia Zhang, Jinliang Deng, Hao Liu

关键词：神经架构搜索，交通预测

4 Conservation-informed Graph Learning for Spatiotemporal Dynamics Prediction

链接：https://dl.acm.org/doi/10.1145/3690624.3709244

作者：Yuan Mi, Pu Ren, Hongteng Xu, Hongsheng Liu, Zidong Wang, Yike Guo, Ji-Rong Wen, Hao Sun, Yang Liu

关键词：时空预测，AI4Science

5 Spatially Compact Dense Block Mining in Spatial Tensors

链接：https://dl.acm.org/doi/10.1145/3690624.3709221

作者：Weike Tang, Dingming Wu, Tsz Nam Chan, Kezhong Lu

关键词：空间张量

6 ProST: Prompt Future Snapshot on Dynamic Graphs for Spatio-Temporal Prediction

链接：https://dl.acm.org/doi/10.1145/3690624.3709273

作者：Kaiwen Xia, Li Lin, Shuai Wang, Qi Zhang, Shuai Wang, Tian He

关键词：稳健交通预测，动态图

7 Seeing the Unseen: Learning Basis Confounder Representations for Robust Traffic Prediction

链接：https://dl.acm.org/doi/10.1145/3690624.3709201

代码：https://github.com/bigscity/STEVE_CODE

作者：Jiahao Ji, Wentao Zhang, Jingyuan Wang, Chao Huang

8 Grid and Road Expressions Are Complementary for Trajectory Representation Learning

链接：https://dl.acm.org/doi/10.1145/3690624.3709272

代码：https://github.com/slzhou-xy/GREEN

作者：Silin Zhou, Shuo Shang, Lisi Chen, Peng Han, Christian S. Jensen

9 Revisiting Synthetic Human Trajectories: Imitative Generation and Benchmarks Beyond Datasaurus

链接：https://dl.acm.org/doi/10.1145/3690624.3709180

作者：Bangchao Deng, Xin Jing, Tianyue Yang, Bingqing Qu, Dingqi Yang, Philippe Cudré-Mauroux

关键词：人类轨迹数据（生成），移动模式，评测

10 A Universal Model for Human Mobility Prediction

作者：Qingyue Long, Yuan Yuan, Yong Li

链接：https://dl.acm.org/doi/10.1145/3690624.3709236

关键词：人群活动预测，流量预测，统一建模

11 CausalMob: Causal Human Mobility Prediction with LLMs-derived Human Intentions toward Public Events

作者：Xiaojie Yang, Hangli Ge, Jiawei Wang, Zipei Fan, Renhe Jiang, Ryosuke Shibasaki, Noboru Koshizuka

链接：https://dl.acm.org/doi/10.1145/3690624.3709236

关键词：人群活动预测，因果分析

12 CoopRide: Cooperate All Grids in City-Scale Ride-Hailing Dispatching with Multi-Agent Reinforcement Learning

链接：https://dl.acm.org/doi/10.1145/3690624.3709205

代码： https://github.com/tsinghua-fib-lab/CoopRide

作者： Jingwei Wang, Qianyue Hao, Wenzhen Huang, Xiaochen Fan, Qin Zhang, Zhentao Tang, Bin Wang, Jianye Hao, Yong Li

关键词：网约车调度，多智能体强化学习

13 MM-Path: Multi-modal, Multi-granularity Path Representation Learning

链接：https://dl.acm.org/doi/10.1145/3690624.3709209

代码： https://github.com/decisionintelligence/MM-Path

作者： Ronghui Xu, Hanyin Cheng, Chenjuan Guo, Hongfan Gao, Jilin Hu, Sean Bin Yang, Bin Yang

关键词：路径表征学习， 多模态， 自监督学习

ADS Track

14 LDMapNet-U: An End-to-End System for City-Scale Lane-Level Map Updating

链接：https://dl.acm.org/doi/10.1145/3690624.3709383

作者：Deguo Xia, Weiming Zhang, Xiyan Liu, Wei Zhang, Chenting Gong, Xiao Tan, Jizhou Huang, Mengmeng Yang, Diange Yang

关键词：车道级地图更新

15 DynST: Dynamic Sparse Training for Resource-Constrained Spatio-Temporal Forecasting

链接：https://dl.acm.org/doi/10.1145/3690624.3709391

作者：Hao Wu, Haomin Wen, Guibin Zhang, Yutong Xia, Yuxuan Liang, Yu Zheng, Qingsong Wen, Kun Wang

关键词：稀疏性，资源受限的时空预测

16 Large-scale Human Mobility Data Regeneration for Open Urban Research.

链接：https://dl.acm.org/doi/10.1145/3690624.3709380

代码：https://github.com/Rising0321/FinalOpenUR.

作者： Ruixing Zhang, Yunqi Liu, Liangzhe Han, Leilei Sun, Chuanren Liu, Jibin Wang, Weifeng Lv

关键词：人群移动模式

17 LLMLight: Large Language Models as Traffic Signal Control Agents

链接：https://dl.acm.org/doi/10.1145/3690624.3709379

代码：https://github.com/usail-hkust/LLMTSCS

作者：Siqi Lai, Zhao Xu, Weijia Zhang, Hao Liu, Hui Xiong

关键词：信控优化，大模型

18 FuzzyLight: A Robust Two-Stage Fuzzy Approach for Traffic Signal Control Works in Real Cities

链接：https://dl.acm.org/doi/10.1145/3690624.3709393

代码：https://dl.acm.org/doi/10.1145/3690624.3709393

作者：Mingyuan Li, Jiahao Wang, Bo Du, Jun Shen, Qiang Wu

关键词：信控优化