Controlling Graph Dynamics with Reinforcement Learning and Graph Neural Networks

被引:0
|
作者
Meirom, Eli A. [1 ]
Maron, Haggai [1 ]
Mannor, Shie [1 ]
Chechik, Gal [1 ]
机构
[1] NVIDIA Res, Tel Aviv, Israel
关键词
DISEASE;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
We consider the problem of controlling a partially-observed dynamic process on a graph by a limited number of interventions. This problem naturally arises in contexts such as scheduling virus tests to curb an epidemic; targeted marketing in order to promote a product; and manually inspecting posts to detect fake news spreading on social networks. We formulate this setup as a sequential decision problem over a temporal graph process. In face of an exponential state space, combinatorial action space and partial observability, we design a novel tractable scheme to control dynamical processes on temporal graphs. We successfully apply our approach to two popular problems that fall into our framework: prioritizing which nodes should be tested in order to curb the spread of an epidemic, and influence maximization on a graph.
引用
收藏
页数:13
相关论文
共 50 条
  • [1] Counterfactual based reinforcement learning for graph neural networks
    Pham, David
    Zhang, Yongfeng
    [J]. ANNALS OF OPERATIONS RESEARCH, 2022,
  • [2] Reinforcement Learning Enhanced Explainer for Graph Neural Networks
    Shan, Caihua
    Shen, Yifei
    Zhang, Yao
    Li, Xiang
    Li, Dongsheng
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [3] Graph Partitioning and Sparse Matrix Ordering using Reinforcement Learning and Graph Neural Networks
    Gatti, Alice
    Hu, Zhixiong
    Smidt, Tess
    Ng, Esmond G.
    Ghysels, Pieter
    [J]. JOURNAL OF MACHINE LEARNING RESEARCH, 2022, 23
  • [4] Graph Partitioning and Sparse Matrix Ordering using Reinforcement Learning and Graph Neural Networks
    Gatti, Alice
    Hu, Zhixiong
    Smidt, Tess
    Ng, Esmond G.
    Ghysels, Pieter
    [J]. Journal of Machine Learning Research, 2022, 23
  • [5] Learning graph normalization for graph neural networks
    Chen, Yihao
    Tang, Xin
    Qi, Xianbiao
    Li, Chun-Guang
    Xiao, Rong
    [J]. NEUROCOMPUTING, 2022, 493 : 613 - 625
  • [6] Learning Graph Dynamics using Deep Neural Networks
    Narayan, Apurva
    Roe, Peter H. O'N
    [J]. IFAC PAPERSONLINE, 2018, 51 (02): : 433 - 438
  • [7] Learning Physical Dynamics with Subequivariant Graph Neural Networks
    Han, Jiaqi
    Huang, Wenbing
    Ma, Hengbo
    Li, Jiachen
    Tenenbaum, Joshua B.
    Gan, Chuang
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 35 (NEURIPS 2022), 2022,
  • [8] Graph Structure Learning for Robust Graph Neural Networks
    Jin, Wei
    Ma, Yao
    Liu, Xiaorui
    Tang, Xianfeng
    Wang, Suhang
    Tang, Jiliang
    [J]. KDD '20: PROCEEDINGS OF THE 26TH ACM SIGKDD INTERNATIONAL CONFERENCE ON KNOWLEDGE DISCOVERY & DATA MINING, 2020, : 66 - 74
  • [9] Reinforcement Learning using Physics Inspired Graph Convolutional Neural Networks
    Wu, Tong
    Scaglione, Anna
    Arnold, Daniel
    [J]. 2022 58TH ANNUAL ALLERTON CONFERENCE ON COMMUNICATION, CONTROL, AND COMPUTING (ALLERTON), 2022,
  • [10] Heterogeneous Graph Structure Learning for Graph Neural Networks
    Zhao, Jianan
    Wang, Xiao
    Shi, Chuan
    Hu, Binbin
    Song, Guojie
    Ye, Yanfang
    [J]. THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 4697 - 4705