STGEN: Deep Continuous-Time Spatiotemporal Graph Generation

被引:1
|
作者
Ling, Chen [1 ]
Cao, Hengning [2 ]
Zhao, Liang [1 ]
机构
[1] Emory Univ, Atlanta, GA 30322 USA
[2] Cornell Univ, Ithaca, NY USA
来源
MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2022, PT III | 2023年 / 13715卷
基金
美国国家科学基金会;
关键词
Deep graph generation; Spatiotemporal graph; Deep generative model;
D O I
10.1007/978-3-031-26409-2_21
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Spatiotemporal graph generation has realistic social significance since it unscrambles the underlying distribution of spatio-temporal graphs from another perspective and fuels substantial spatio-temporal data mining tasks. Generative models for temporal and spatial networks respectively cannot be easily generalized to spatiotemporal graph generation due to their incapability of capturing: 1) mutually influenced graph and spatiotemporal distribution, 2) spatiotemporal-validity constraints, and 3) characteristics of multi-modal spatiotemporal properties. To this end, we propose a generic and end-to-end jointly captures the graph, temporal, and spatial distributions of spatiotemporal graphs. Particularly, STGEN learns the multi-modal distribution of spatiotemporal graphs via learning the distribution of spatiotemporal walks based on a new heterogeneous probabilistic sequential model. Auxiliary activation layers are proposed to retain the spatiotemporal validity of the generated graphs. In addition, a new boosted strategy for the ensemble of discriminators is proposed to distinguish the generated and real spatiotemporal walks from multi-dimensions and capture the combinatorial patterns among them. Finally, extensive experiments are conducted on both synthetic/real-world spatio-temporal graphs and demonstrated the efficacy of the proposed model.
引用
收藏
页码:340 / 356
页数:17
相关论文
共 50 条
  • [1] Continuous-time quantum walks on a cycle graph
    Solenov, D
    Fedichkin, L
    PHYSICAL REVIEW A, 2006, 73 (01)
  • [2] Continuous-Time Graph Representation with Sequential Survival Process
    Celikkanat, Abdulkadir
    Nakis, Nikolaos
    Morup, Morten
    THIRTY-EIGHTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 38 NO 10, 2024, : 11177 - 11185
  • [3] Learning Graph ODE for Continuous-Time Sequential Recommendation
    Qin, Yifang
    Ju, Wei
    Wu, Hongjun
    Luo, Xiao
    Zhang, Ming
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2024, 36 (07) : 3224 - 3236
  • [4] Implementation of a continuous-time quantum walk on a sparse graph
    Chen, Zhaoyang
    Li, Guanzhong
    Li, Lvzhou
    PHYSICAL REVIEW A, 2024, 110 (05)
  • [5] The Stationary Distribution of a Continuous-Time Random Graph Process
    韩东
    数学季刊, 1994, (02) : 64 - 68
  • [6] Continuous-Time Graph Learning for Cascade Popularity Prediction
    Lu, Xiaodong
    Ji, Shuo
    Yu, Le
    Sun, Leilei
    Du, Bowen
    Zhu, Tongyu
    PROCEEDINGS OF THE THIRTY-SECOND INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, IJCAI 2023, 2023, : 2224 - 2232
  • [7] Continuous-Time Temporal Graph Learning on Provenance Graphs
    Reha, Jakub
    Lovisotto, Giulio
    Russo, Michele
    Gravina, Alessio
    Grohnfeldt, Claas
    2023 23RD IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS, ICDMW 2023, 2023, : 1131 - 1140
  • [8] TG-GAN: Continuous-time Temporal Graph Deep Generative Models with Time-Validity Constraints
    Zhang, Liming
    Zhao, Liang
    Qin, Shan
    Pfoser, Dieter
    Ling, Chen
    PROCEEDINGS OF THE WORLD WIDE WEB CONFERENCE 2021 (WWW 2021), 2021, : 2104 - 2116
  • [9] Continuous-Time Deep Glioma Growth Models
    Petersen, Jens
    Isensee, Fabian
    Koehler, Gregor
    Jaeger, Paul F.
    Zimmerer, David
    Neuberger, Ulf
    Wick, Wolfgang
    Debus, Jurgen
    Heiland, Sabine
    Bendszus, Martin
    Vollmuth, Philipp
    Maier-Hein, Klaus H.
    MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2021, PT III, 2021, 12903 : 83 - 92
  • [10] Continuous-time identification of continuous-time systems
    Kowalczuk, Z
    Kozlowski, J
    (SYSID'97): SYSTEM IDENTIFICATION, VOLS 1-3, 1998, : 1293 - 1298