KDD 2024 时空数据(Spatio-temporal) ADS论文总结

2024-09-07 14:36

本文主要是介绍KDD 2024 时空数据(Spatio-temporal) ADS论文总结,希望对大家解决编程问题提供一定的参考价值,需要的开发者们随着小编来一起学习吧!

2024 KDD( ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 知识发现和数据挖掘会议)在2024年8月25日-29日在西班牙巴塞罗那举行。

本文总结了KDD2024有关时空数据(Spatial-temporal) 的相关论文,如有疏漏,欢迎大家补充。

时空数据Topic:时空(交通)预测, 生成,拥堵预测,定价预测,气象预测,轨迹生成,预测,异常检测,信控优化等

ADS track中有2个session中与时空数据(城市计算)紧密相关:Spatiotemporal Applications 与 Urban Mobility,还有一些其余session中有一些做的时空数据任务。

KDD 2024 时空数据(Spatial-temporal) ADS论文总结
Spatiotemporal Applications

  1. Transportation Marketplace Rate Forecast Using Signature Transform
  2. MARLP: Time-series Forecasting Control for Agricultural Managed Aquifer Recharge
  3. Diffusion Model-based Mobile Traffic Generation with Open Data for Network Planning and Optimization
  4. LaDe: The First Comprehensive Last-mile Express Dataset from Industry
  5. UrbanGPT: Spatio-Temporal Large Language Models
  6. Spatio-Temporal Consistency Enhanced Differential Network for Interpretable Indoor Temperature Prediction
  7. Weather Knows What Will Occur: Urban Public Nuisance Events Prediction and Control with Meteorological Assistance

Urban Mobility

  1. Interpretable Cascading Mixture-of-Experts for Urban Traffic Congestion Prediction
  2. TrajRecovery: An Efficient Vehicle Trajectory Recovery Framework based on Urban-Scale Traffic Camera Records
  3. DuMapNet: An End-to-End Vectorization System for City-Scale Lane-Level Map Generation
  4. An Offline Meta Black-box Optimization Framework for Adaptive Design of Urban Traffic Light Management Systems
  5. FedGTP: Exploiting Inter-Client Spatial Dependency in Federated Graph-based Traffic Prediction
  6. PEMBOT: Pareto-Ensembled Multi-task Boosted Trees

其他

  1. FusionSF: Fuse Heterogeneous Modalities in a Vector Quantized Framework for Robust Solar Power Forecasting

🌟【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在这里插入图片描述

Spatiotemporal Applications

1. Transportation Marketplace Rate Forecast Using Signature Transform

ACM链接https://dl.acm.org/doi/abs/10.1145/3637528.3671637

链接https://arxiv.org/abs/2401.04857

作者:Haotian Gu (University of California, Berkeley); Xin Guo (Worldwide Operations Research Science, Amazon.com Inc., University of California, Berkeley); Timothy L. Jacobs (Worldwide Operations Research Science, Amazon.com Inc.); Philip Kaminsky (Worldwide Operations Research Science, Amazon.com Inc., University of California, Berkeley); Xinyu Li (University of California, Berkeley)

关键词:运价预测

2. MARLP: Time-series Forecasting Control for Agricultural Managed Aquifer Recharge

ACM链接https://dl.acm.org/doi/abs/10.1145/3637528.3671533

链接https://arxiv.org/abs/2407.01005

作者:Yuning Chen (University of California, Merced); Kang Yang (University of California, Merced); Zhiyu An (University of California, Merced); Brady Holder (University of California, Agriculture and Natural Resources); Luke Paloutzian (University of California, Agriculture and Natural Resources); Khaled M. Bali (University of California, Agriculture and Natural Resources); Wan Du (University of California, Merced)

关键词:时序预测,因果学习,模型预测控制

MARLP

3. Diffusion Model-based Mobile Traffic Generation with Open Data for Network Planning and Optimization

ACM链接https://dl.acm.org/doi/abs/10.1145/3637528.3671544

作者:Haoye Chai (Department of Electronic Engineering, BNRist, Tsinghua University); Tao Jiang (Research Center of 6G Mobile Communications, School of Cyber Science and Engineering, Huazhong University of Science and Technology); Li Yu (Chinamobile Research Institute)

关键词:交通数据生成,扩散模型,卫星图像

OpenDiff

4. LaDe: The First Comprehensive Last-mile Express Dataset from Industry

ACM链接https://dl.acm.org/doi/abs/10.1145/3637528.3671548

链接https://arxiv.org/abs/2306.10675

代码https://github.com/wenhaomin/LaDe

作者:Lixia Wu (Cainiao Network); Haomin Wen (School of Computer and Information Technology, Beijing Jiaotong University, Cainiao Network); Haoyuan Hu (Cainiao Network); Xiaowei Mao (School of Computer and Information Technology, Beijing Jiaotong University, Cainiao Network); Yutong Xia (National University of Singapore); Ergang Shan (Cainiao Network); Jianbin Zheng (Artificial Intelligence Department, Cainiao Network); Junhong Lou (Cainiao Network); Yuxuan Liang (Hong Kong University of Science and Technology (Guangzhou)); Liuqing Yang (Hong Kong University of Science and Technology (Guangzhou)); Roger Zimmermann (National University of Singapore); Youfang Lin (School of Computer and Information Technology, Beijing Jiaotong Univercity); Huaiyu Wan (School of Computer and Information Technology, Beijing Jiaotong University)

关键词:物流数据集,最后一公里配送

LaDe

5. UrbanGPT: Spatio-Temporal Large Language Models

ACM链接https://dl.acm.org/doi/abs/10.1145/3637528.3671578

链接https://arxiv.org/abs/2403.00813

代码https://github.com/HKUDS/UrbanGPT

作者:Zhonghang Li (South China University of Technology, The University of Hong Kong); Lianghao Xia (The University of Hong Kong); Jiabin Tang (The University of Hong Kong); Yong Xu (South China University of Technology); Lei Shi (Baidu Inc.); Long Xia (Baidu Inc.); Dawei Yin (Baidu Inc.); Chao Huang (The University of Hong Kong)

关键词:交通预测,大模型

备注:没有部署的ADS

UrbanGPT

6. Spatio-Temporal Consistency Enhanced Differential Network for Interpretable Indoor Temperature Prediction

ACM链接https://dl.acm.org/doi/abs/10.1145/3637528.3671608

作者:Dekang Qi (Southwest Jiaotong University, JD iCity, JD Technology); Xiuwen Yi (JD iCity, JD Technology, JD Intelligent Cities Research); Chengjie Guo (Xidian University); Yanyong Huang (Southwestern University of Finance and Economics); Junbo Zhang (JD iCity, JD Technology, JD Intelligent Cities Research); Tianrui Li (Southwest Jiaotong University); Yu Zheng (JD iCity, JD Technology, JD Intelligent Cities Research)

关键词:室内温度预测,可解释性预测,时空一致性

CONST

7. Weather Knows What Will Occur: Urban Public Nuisance Events Prediction and Control with Meteorological Assistance

ACM链接https://dl.acm.org/doi/abs/10.1145/3637528.3671639

作者:Yi Xie (Fudan University); Tianyu Qiu (Fudan University); Yun Xiong (Fudan University); Xiuqi Huang (Shanghai Jiaotong University); Xiaofeng Gao (Shanghai Jiao Tong University); Chao Chen (Sorbonne Université – Faculté des Sciences (Paris VI)); Qiang Wang (Shanghai Center for Meteorological Disaster Prevention Technology); Haihong Li (Shanghai Center for Meteorological Disaster Prevention Technology)

关键词:气象辅助的城市事件预测

ST-T3

Urban Mobility

8. Interpretable Cascading Mixture-of-Experts for Urban Traffic Congestion Prediction

链接https://arxiv.org/abs/2406.12923

ACM链接https://dl.acm.org/doi/abs/10.1145/3637528.3671507

作者:Wenzhao Jiang (The Hong Kong University of Science and Technology (Guangzhou)); Jindong Han (The Hong Kong University of Science and Technology); Hao Liu (The Hong Kong University of Science and Technology (Guangzhou), The Hong Kong University of Science and Technology); Tao Tao (Didichuxing Co. Ltd); Naiqiang Tan (Didichuxing Co. Ltd); Hui Xiong (The Hong Kong University of Science and Technology (Guangzhou), The Hong Kong University of Science and Technology)

关键词:拥堵预测,混合专家系统

CP-MoE

9. TrajRecovery: An Efficient Vehicle Trajectory Recovery Framework based on Urban-Scale Traffic Camera Records

ACM链接https://dl.acm.org/doi/abs/10.1145/3637528.3671558

作者:Dongen Wu (Zhejiang University); Ziquan Fang (Zhejiang University); Qichen Sun (Zhejiang University); Lu Chen (Zhejiang University); Haiyang Hu (Zhejiang University); Fei Wang (Zhejiang University); Yunjun Gao (Zhejiang University)

关键词:轨迹恢复

10. DuMapNet: An End-to-End Vectorization System for City-Scale Lane-Level Map Generation

ACM链接https://dl.acm.org/doi/abs/10.1145/3637528.3671579

链接https://arxiv.org/abs/2406.14255

代码https://github.com/XiyanLiu/DuMapNet

作者:Deguo Xia (Tsinghua University, Baidu Inc.); Weiming Zhang (Baidu Inc.); Xiyan Liu (Baidu Inc.); Wei Zhang (Baidu Inc.); Chenting Gong (Baidu Inc.); Jizhou Huang (Baidu Inc.); Mengmeng Yang (Tsinghua University); Diange Yang (Tsinghua University)

关键词:城市车道级别地图生成

DuMapNet

11. An Offline Meta Black-box Optimization Framework for Adaptive Design of Urban Traffic Light Management Systems

ACM链接https://dl.acm.org/doi/abs/10.1145/3637528.3671606

链接https://arxiv.org/abs/2408.07327

作者:Taeyoung Yun (KAIST); Kanghoon Lee (KAIST); Sujin Yun (KAIST); Ilmyung Kim (Korea Telecom); Won-Woo Jung (Korea Telecom); Min-Cheol Kwon (Korea Telecom); Kyujin Choi (Korea Telecom); Yoohyeon Lee (Korea Telecom); Jinkyoo Park (KAIST)

关键词:交通灯,元学习,黑盒优化

12. FedGTP: Exploiting Inter-Client Spatial Dependency in Federated Graph-based Traffic Prediction

链接https://zhouzimu.github.io/paper/kdd24-yang.pdf

ACM链接https://dl.acm.org/doi/abs/10.1145/3637528.3671613

代码https://github.com/LarryHawkingYoung/KDD2024_FedGTP

作者:Linghua Yang (SKLCCSE Lab, Beihang University); Wantong Chen (SKLCCSE Lab, Beihang University); Xiaoxi He (Faculty of Science and Technology, University of Macau); Shuyue Wei (SKLCCSE Lab, Beihang University); Yi Xu (SKLCCSE Lab, Institute of Artificial Intelligence, Beihang University); Zimu Zhou (School of Data Science, City University of Hong Kong); Yongxin Tong (SKLCCSE Lab, Beihang University)

关键词:交通预测,联邦学习

image-20240821172213246

13. PEMBOT: Pareto-Ensembled Multi-task Boosted Trees

链接https://www.amazon.science/publications/pembot-pareto-ensembled-multi-task-boosted-trees

ACM链接https://dl.acm.org/doi/abs/10.1145/3637528.3671619

作者:Gokul Swamy (International Machine Learning, Amazon); Anoop Saladi (International Machine Learning, Amazon); Arunita Das (International Machine Learning, Amazon); Shobhit Niranjan (International Machine Learning, Amazon)

关键词:帕累托最优,多任务

其他

14. FusionSF: Fuse Heterogeneous Modalities in a Vector Quantized Framework for Robust Solar Power Forecasting

链接https://arxiv.org/abs/2402.05823

ACM链接https://dl.acm.org/doi/abs/10.1145/3637528.3671509

作者:Ziqing Ma (DAMO Academy, Alibaba Group); Wenwei Wang (DAMO Academy, Alibaba Group); Tian Zhou (DAMO Academy, Alibaba Group); Chao Chen (DAMO Academy, Central South University); Bingqing Peng (DAMO Academy, Alibaba Group); Liang Sun (DAMO Academy, Alibaba Group); Rong Jin (DAMO Academy, Alibaba Group)

关键词:太阳能预测,模态聚合,向量量化,零样本

FusionSF

相关链接

; Bingqing Peng (DAMO Academy, Alibaba Group); Liang Sun (DAMO Academy, Alibaba Group); Rong Jin (DAMO Academy, Alibaba Group)

关键词:太阳能预测,模态聚合,向量量化,零样本

[外链图片转存中…(img-n0idp4l1-1725679952235)]

相关链接

KDD 2024 Applied Data Science Paperhttps://kdd2024.kdd.org/applied-data-science-track-papers/

🌟【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在这里插入图片描述

这篇关于KDD 2024 时空数据(Spatio-temporal) ADS论文总结的文章就介绍到这儿,希望我们推荐的文章对编程师们有所帮助!



http://www.chinasem.cn/article/1145326

相关文章

Python MySQL如何通过Binlog获取变更记录恢复数据

《PythonMySQL如何通过Binlog获取变更记录恢复数据》本文介绍了如何使用Python和pymysqlreplication库通过MySQL的二进制日志(Binlog)获取数据库的变更记录... 目录python mysql通过Binlog获取变更记录恢复数据1.安装pymysqlreplicat

Linux使用dd命令来复制和转换数据的操作方法

《Linux使用dd命令来复制和转换数据的操作方法》Linux中的dd命令是一个功能强大的数据复制和转换实用程序,它以较低级别运行,通常用于创建可启动的USB驱动器、克隆磁盘和生成随机数据等任务,本文... 目录简介功能和能力语法常用选项示例用法基础用法创建可启动www.chinasem.cn的 USB 驱动

Oracle数据库使用 listagg去重删除重复数据的方法汇总

《Oracle数据库使用listagg去重删除重复数据的方法汇总》文章介绍了在Oracle数据库中使用LISTAGG和XMLAGG函数进行字符串聚合并去重的方法,包括去重聚合、使用XML解析和CLO... 目录案例表第一种:使用wm_concat() + distinct去重聚合第二种:使用listagg,

Python实现将实体类列表数据导出到Excel文件

《Python实现将实体类列表数据导出到Excel文件》在数据处理和报告生成中,将实体类的列表数据导出到Excel文件是一项常见任务,Python提供了多种库来实现这一目标,下面就来跟随小编一起学习一... 目录一、环境准备二、定义实体类三、创建实体类列表四、将实体类列表转换为DataFrame五、导出Da

Python实现数据清洗的18种方法

《Python实现数据清洗的18种方法》本文主要介绍了Python实现数据清洗的18种方法,文中通过示例代码介绍的非常详细,对大家的学习或者工作具有一定的参考学习价值,需要的朋友们下面随着小编来一起学... 目录1. 去除字符串两边空格2. 转换数据类型3. 大小写转换4. 移除列表中的重复元素5. 快速统

Python数据处理之导入导出Excel数据方式

《Python数据处理之导入导出Excel数据方式》Python是Excel数据处理的绝佳工具,通过Pandas和Openpyxl等库可以实现数据的导入、导出和自动化处理,从基础的数据读取和清洗到复杂... 目录python导入导出Excel数据开启数据之旅:为什么Python是Excel数据处理的最佳拍档

Python中实现进度条的多种方法总结

《Python中实现进度条的多种方法总结》在Python编程中,进度条是一个非常有用的功能,它能让用户直观地了解任务的进度,提升用户体验,本文将介绍几种在Python中实现进度条的常用方法,并通过代码... 目录一、简单的打印方式二、使用tqdm库三、使用alive-progress库四、使用progres

在Pandas中进行数据重命名的方法示例

《在Pandas中进行数据重命名的方法示例》Pandas作为Python中最流行的数据处理库,提供了强大的数据操作功能,其中数据重命名是常见且基础的操作之一,本文将通过简洁明了的讲解和丰富的代码示例,... 目录一、引言二、Pandas rename方法简介三、列名重命名3.1 使用字典进行列名重命名3.编

Python使用Pandas库将Excel数据叠加生成新DataFrame的操作指南

《Python使用Pandas库将Excel数据叠加生成新DataFrame的操作指南》在日常数据处理工作中,我们经常需要将不同Excel文档中的数据整合到一个新的DataFrame中,以便进行进一步... 目录一、准备工作二、读取Excel文件三、数据叠加四、处理重复数据(可选)五、保存新DataFram

使用Java解析JSON数据并提取特定字段的实现步骤(以提取mailNo为例)

《使用Java解析JSON数据并提取特定字段的实现步骤(以提取mailNo为例)》在现代软件开发中,处理JSON数据是一项非常常见的任务,无论是从API接口获取数据,还是将数据存储为JSON格式,解析... 目录1. 背景介绍1.1 jsON简介1.2 实际案例2. 准备工作2.1 环境搭建2.1.1 添加