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
下载
收藏
页数:13
相关论文
共 50 条
  • [21] Field-informed Reinforcement Learning of Collective Tasks with Graph Neural Networks
    Aguzzi, Gianluca
    Viroli, Mirko
    Esterle, Lukas
    2023 IEEE INTERNATIONAL CONFERENCE ON AUTONOMIC COMPUTING AND SELF-ORGANIZING SYSTEMS, ACSOS, 2023, : 37 - 46
  • [22] Combining Deep Reinforcement Learning With Graph Neural Networks for Optimal VNF Placement
    Sun, Penghao
    Lan, Julong
    Li, Junfei
    Guo, Zehua
    Hu, Yuxiang
    IEEE COMMUNICATIONS LETTERS, 2021, 25 (01) : 176 - 180
  • [23] A Deep Reinforcement Learning Heuristic for SAT based on Antagonist Graph Neural Networks
    Fournier, Thomas
    Lallouet, Arnaud
    Cropsal, Telio
    Glorian, Gael
    Papadopoulos, Alexandre
    Petitet, Antoine
    Perez, Guillaume
    Sekar, Suruthy
    Suijlen, Wijnand
    2022 IEEE 34TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, ICTAI, 2022, : 1218 - 1222
  • [24] Non-Parametric Graph Learning for Bayesian Graph Neural Networks
    Pal, Soumyasundar
    Malekmohammadi, Saber
    Regol, Florence
    Zhang, Yingxue
    Xu, Yishi
    Coates, Mark
    CONFERENCE ON UNCERTAINTY IN ARTIFICIAL INTELLIGENCE (UAI 2020), 2020, 124 : 1318 - 1327
  • [25] Learning graph in graph convolutional neural networks for robust seizure prediction
    Lian, Qi
    Qi, Yu
    Pan, Gang
    Wang, Yueming
    JOURNAL OF NEURAL ENGINEERING, 2020, 17 (03)
  • [26] Graph-to-Sequence Learning using Gated Graph Neural Networks
    Beck, Daniel
    Haffari, Gholamreza
    Cohn, Trevor
    PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL), VOL 1, 2018, : 273 - 283
  • [27] Towards Bayesian Learning of the Architecture, Graph and Parameters for Graph Neural Networks
    Valkanas, Antonios
    Panzini, Andre-Walter
    Coates, Mark
    2022 56TH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS, AND COMPUTERS, 2022, : 852 - 856
  • [28] Decision-focused Graph Neural Networks for Graph Learning and Optimization
    Liu, Yang
    Zhou, Chuan
    Zhang, Peng
    Zhang, Shuai
    Zhang, Xiaoou
    Li, Zhao
    Chen, Hongyang
    23RD IEEE INTERNATIONAL CONFERENCE ON DATA MINING, ICDM 2023, 2023, : 1151 - 1156
  • [29] Graph alternate learning for robust graph neural networks in node classification
    Baoliang Zhang
    Xiaoxin Guo
    Zhenchuan Tu
    Jia Zhang
    Neural Computing and Applications, 2022, 34 : 8723 - 8735
  • [30] Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology
    Dehmamy, Nima
    Barabasi, Albert-Laszlo
    Yu, Rose
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32