KDD 2023 | 时空数据（Spatial-Temporal）Research论文总结
KDD 2023 | 时空数据（Spatial-Temporal）Research论文总结
2023 KDD论文接收情况：Research track（研究赛道）接收率：22.1%（313/1416），ADS Track（Applied Data Science，应用数据科学赛道）接收率：25.4%（184/725）。
（蹭一下KDD 2024第一轮Rebuttal的热度，预祝各位rebuttal顺利。）
本文总结了在两个赛道时空数据学习的相关论文（如有疏漏，欢迎大家补充），ADS Track在次条
Research track中有3个session中与时空数据（城市计算）紧密相关，还有一些其余session中有一些做的时空数据任务。
Research Track Topic：时空预测，信控优化，轨迹表示学习，多模态，神经过程，迁移学习等。
Spatiotemporal Data
1. Maintaining the Status Quo: Capturing Invariant Relations for OOD Spatiotemporal Learning
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599421
代码：https://github.com/zzyy0929/KDD23-CauSTG
作者：Zhengyang Zhou (University of Science and Technology of China), Qihe Huang (University of Science and Technology of China), Kuo Yang (University of Science and Technology of China), Kun Wang (University of Science and Technology of China), Xu Wang (University of Science and Technology of China), Yudong Zhang (University of Science and Technology of China), Yuxuan Liang (University of Science and Technology of China), Yang Wang (University of Science and Technology of China)
关键词：分布外泛化，时空OOD，因果学习，不变学习，动态图
CauSTG
2. Generalizable Low-Resource Activity Recognition with Diverse and Discriminative Representation Learning
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599360
代码：https://github.com/microsoft/robustlearn
作者：Xin Qin (Beijing Key Lab. of Mobile Com., CAS), Jindong Wang (Microsoft Research Asia), Shuo Ma (Beijing Key Lab. of Mobile Com., CAS), Wang Lu (Beijing Key Lab. of Mobile Com., CAS), Yongchun Zhu (Beijing Key Lab. of Mobile Com., CAS), Xin Xie (Microsoft Research Asia), Yiqiang Chen (Beijing Key Lab. of Mobile Com., CAS)
关键词：普适计算，迁移学习
DDLearn
3. Localised Adaptive Spatial-Temporal Graph Neural Network
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599418
作者：Wenying Duan (Nanchang University), Xiaoxi He (University of Macau), Zimu Zhou (City University of Hong Kong), Lothar Thiele (ETH Zurich), Hong Rao (Nanchang University)
关键词：时空预测，时空图神经网络，稀疏图
ASTGNNs
4. Spatio-Temporal Diffusion Point Processes
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599511
代码：https://github.com/tsinghua-fib-lab/Spatio-temporal-Diffusion-Point-Processes
作者：Yuan Yuan (Department of Electronic Engineering, Tsinghua University), Jingtao Ding (Department of Electronic Engineering, Tsinghua University), Chenyang Shao (Department of Electronic Engineering, Tsinghua University), Depeng Jin (Department of Electronic Engineering, Tsinghua University), Yong Li (Department of Electronic Engineering, Tsinghua University)
关键词：扩散模型，点过程
DSTPP
5. ST-iFGSM: Enhancing Robustness of Human Mobility Signature Identification Model via Spatial-Temporal Iterative FGSM
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599513
代码：https://github.com/mhu3/ST-Siamese-Attack
作者：Mingzhi Hu (Worcester Polytechnic Institute), Xin Zhang (Worcester Polytechnic Institute), Yanhua Li (Worcester Polytechnic Institute), Xun Zhou (University of Iowa), Jun Luo (Lenovo Group Limited)
关键词：稳健性，对抗攻击，驾驶员检测，异常检测
Spatial-temporal HuMID
6. On Hierarchical Disentanglement of Interactive Behaviors for Multimodal Spatiotemporal Data with Incompleteness
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599448
作者：Jiayi Chen (University of Virginia), Aidong Zhang (University of Virginia)
关键词：多模态时空数据，无监督学习，知识表示和推理，时空解耦，缺失数据，自编码器
Urban Data I
7. Robust Spatiotemporal Traffic Forecasting with Reinforced Dynamic Adversarial Training
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599492
代码：https://github.com/usail-hkust/RDAT
作者：Fan Liu (The Hong Kong University of Science and Technology (Guangzhou)), Weijia Zhang (The Hong Kong University of Science and Technology (Guangzhou)), Hao Liu (The Hong Kong University of Science and Technology (Guangzhou); The Hong Kong University of Science and Technology)
关键词：交通预测、对抗网络，稳健性
RDAT
8. Pattern Expansion and Consolidation on Evolving Graphs for Continual Traffic Prediction
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599463
作者：Binwu Wang (University of Science and Technology of China), Yudong Zhang (University of Science and Technology of China), Xu Wang (University of Science and Technology of China), Pengkun Wang (Suzhou Institute for Advanced Research, University of Science and Technology of China), Zhengyang Zhou (Suzhou Institute for Advanced Research, University of Science and Technology of China), LEI BAI (Shanghai AI Laboratory), Yang Wang (University of Science and Technology of China)
关键词：交通预测、持续学习
PECPM
9. TransformerLight: A Novel Sequence Modeling Based Traffic Signaling Mechanism via Gated Transformer
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599530
代码：https://github.com/Smart-Trafficlab/TransformerLight
作者：Qiang Wu (University of Electronic Science and Technology of China), Mingyuan Li (Beijing University of Posts and Telecommunications), Jun Shen (University of Wollongong), Linyuan Lü(University of Science and Technology of China), Bo Du (University of Wollongong), Ke Zhang (Beijing University of Posts and Telecommunications)
关键词：信控优化
好文分享 |【KDD 2023】TransformerLight：一种基于时序建模的门控Transformer交通信号控制机制
TransformerLight
10. Optimizing Traffic Control with Model-Based Learning: A Pessimistic Approach to Data-Efficient Policy Inference
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599459
代码：https://github.com/siddarth-c/KDD23-ADAC
作者：Mayuresh Kunjir (Amazon Web Services), Sanjay Chawla (Qatar Computing Research Institute, Hamad Bin Khalifa University), Siddarth Chandrasekar (Indian Institute of Technology Madras), Devika Jay (Indian Institute of Technology Madras), Balaraman Ravindran (Indian Institute of Technology Madras)
关键词：信控优化，离线强化学习
11. Mitigating Action Hysteresis in Traffic Signal Control with Traffic Predictive Reinforcement Learning
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599528
作者：Xiao Han (City University of Hong Kong), Xiangyu Zhao (City University of Hong Kong), Liang Zhang (Shenzhen Research Institute of Big Data), Wanyu Wang (City University of Hong Kong)
关键词：信控优化，交通状态预测
KDD 2023｜ 通过交通预测减轻交通信号控制中的动作滞后问题
PRLight
12. Spatial Heterophily Aware Graph Neural Networks
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599510
代码：https://github.com/PaddlePaddle/PaddleSpatial/tree/main/research/SHGNN
作者：Congxi Xiao (University of Science and Technology of China; Baidu Research), Jingbo Zhou (Baidu Research), Jizhou Huang (Baidu Inc.), Tong Xu (University of Science and Technology of China; State Key Laboratory of Cognitive Intelligence), Hui Xiong (The Hong Kong University of Science and Technology (Guangzhou); The Hong Kong University of Science and Technology)
关键词：空间异质性、时空预测
SHGNN
Urban Data II
13. LightPath: Lightweight and Scalable Path Representation Learning
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599415
作者：Sean Bin Yang (Aalborg University), Jilin Hu (East China Normal University), Chenjuan Guo (East China Normal University), Bin Yang (East China Normal University), Christian Jensen (Aalborg University)
关键词：轨迹表示学习，自监督学习，轻量化
LightPath
14. Urban Region Representation Learning with OpenStreetMap Building Footprints
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599538
作者：Yi Li (Nanyang Technological University), Weiming Huang (Nanyang Technological University), Gao Cong (Nanyang Technological University), Hao Wang (Nanyang Technological University), Zheng Wang (Nanyang Technological University)
关键词：表示学习，对比学习，OpenStreetMap，城市区域，地理数据挖掘
RegionDCL
15. Multi-Temporal Relationship Inference in Urban Areas
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599440
作者：Shuangli Li (University of Science and Technology of China; Baidu Research), Jingbo Zhou (Baidu Research), Ji Liu (Baidu Research), Tong Xu (University of Science and Technology of China; State Key Laboratory of Cognitive Intelligenc), Enhong Chen (University of Science and Technology of China; State Key Laboratory of Cognitive Intelligence), Hui Xiong (The Hong Kong University of Science and Technology (Guangzhou); The Hong Kong University of Science and Technology)
关键词：关系推断，空间图
SEENet
16. A Study of Situational Reasoning for Traffic Understanding
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599246
作者：Jiarui Zhang (USC/ISI), Filip Ilievski (USC/ISI), Kaixin Ma (CMU), Aravinda Kollaa (USC/ISI), Jonathan Francis (Bosch), Alessandro Oltramari (Bosch)
关键词：问答模型、交通知识理解
17. Frigate: Frugal Spatio-temporal Forecasting on Road Networks
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599357
代码：https://github.com/idea-iitd/Frigate
作者：Mridul Gupta (Indian Institute of Technology Delhi), Hariprasad Kodamana (Indian Institute of Technology Delhi), Sayan Ranu (Indian Institute of Technology Delhi)
关键词：交通预测
Frigate
其他
18. Graph Neural Processes for Spatio-Temporal Extrapolation
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599372
代码：https://github.com/hjf1997/STGNP
作者：Junfeng Hu (National University of Singapore), Yuxuan Liang (Hong Kong University of Science and Technology (Guangzhou)), Zhencheng Fan (University of Technology Sydney), Hongyang Chen (Zhejiang Lab), Yu Zheng (JD Intelligent Cities Research; JD iCity, JD Technology), Roger Zimmermann (National University of Singapore)
关键词：不确定性量化、神经过程、时空外推
STGNP
19. Deep Bayesian Active Learning for Accelerating Stochastic Simulation
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599300
代码：https://github.com/Rose-STL-Lab/Interactive-Neural-Process
作者：Dongxia Wu (University of California, San Diego), Ruijia Niu (University of California, San Diego), Matteo Chinazzi (Northeastern University), Alessandro Vespignani (Northeastern University), Yi-An Ma (University of California, San Diego), Rose Yu (University of California, San Diego)
关键词：不确定性量化、神经过程，贝叶斯主动学习
INP
20. Generative Causal Interpretation Model for Spatio-Temporal Representation Learning
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599363
代码：https://github.com/EternityZY/GCIM
作者：Yu Zhao (Beihang University), Pan Deng (Beihang University), Junting Liu (Beihang University), Xiaofeng Jia (Beijing Big Data Centre), Jianwei Zhang (Capinfo Company Limited)
关键词：生成因果模型、时空表示学习
GCIM
21. MM-DAG: Multi-task DAG Learning for Multi-Modal Data with Application for Traffic Congestion Analysis
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599436
代码：https://github.com/Lantian72/MM-DAG
作者：Tian Lan (Tsinghua University), Ziyue Li (University of Cologne), zhishuai Li (SenseTime Research), Lei Bai (Shanghai AI Laboratory), Man Li (The Hong Kong University of Science and Technology), Fugee Tsung (The Hong Kong University of Science and Technology (Guangzhou)), Wolfgang Ketter (University of Cologne), Rui Zhao (SenseTime Research), Chen Zhang (Tsinghua University)
关键词：因果学习、交通拥堵，有向无环图，多任务学习，多模态数据
22.Transferable Graph Structure Learning for Graph-Based Traffic Forecasting Across Cities
链接：https://dl.acm.org/doi/abs/10.1145/3580305.3599529
作者：Yilun Jin (Hong Kong University of Science and Technology), Kai Chen (Hong Kong University of Science and Technology), Qiang Yang (Hong Kong University of Science and Technology; WeBank)
关键词：迁移学习，交通预测
TransGTR
如果觉得有帮助还请分享，在看，点赞
腾讯云开发者
