Hypernetwork Dismantling via Deep Reinforcement Learning

Hypernetwork Dismantling via Deep Reinforcement Learning
复制标题

通过深度强化学习拆除超网络

DOI:
10.1109/tnse.2022.3174163
复制
发表时间:
2021-04
影响因子:
6.6
通讯作者:
Yiwen Zhang
Yiwen Zhang
中科院分区:
计算机科学3区
文献类型:
--
作者:
Dengcheng Yan;Wenxin Xie;Yiwen Zhang

文献摘要

参考文献

相似文献

网络拆除旨在通过删除一组最佳节点来降低网络的连通性。它已被广泛应用于许多现实世界的应用,如流行病控制和谣言遏制。然而,传统的方法通常集中在简单的网络建模,只有成对的相互作用,而超网络建模的组明智的相互作用是无处不在的和关键的。在这项工作中,我们将超网络拆除问题表示为节点序列决策问题,并提出了一个基于深度强化学习(DRL)的超网络拆除框架。此外,我们设计了一种新的归纳超网络嵌入方法,以确保可移植到各种现实世界的超网络。我们的框架首先生成小规模的合成超网络,并将节点和超网络嵌入到一个低维向量空间中,分别表示DRL中的动作和状态空间。然后由智能体在这些合成超网络上进行试错拆解任务,不断优化拆解策略。最后,将优化后的策略应用于现实世界的超网络拆解任务。五个真实世界的超网络上的实验结果证明了我们提出的框架的有效性。
Network dismantling aims to degrade the connectivity of a network by removing an optimal set of nodes. It has been widely adopted in many real-world applications such as epidemic control and rumor containment. However, conventional methods usually focus on simple network modeling with only pairwise interactions, while group-wise interactions modeled by hypernetwork are ubiquitous and critical. In this work, we formulate the hypernetwork dismantling problem as a node sequence decision problem and propose a deep reinforcement learning (DRL)-based hypernetwork dismantling framework. Besides, we design a novel inductive hypernetwork embedding method to ensure the transferability to various real-world hypernetworks. Our framework first generates small-scale synthetic hypernetworks and embeds the nodes and hypernetworks into a low dimensional vector space to represent the action and state space in DRL, respectively. Then trial-and-error dismantling tasks are conducted by an agent on these synthetic hypernetworks, and the dismantling strategy is continuously optimized. Finally, the well-optimized strategy is applied to real-world hypernetwork dismantling tasks. Experimental results on five real-world hypernetworks demonstrate the effectiveness of our proposed framework.
DOI: --
发表时间: 2020-02
期刊: ArXiv
影响因子: --
作者:
S. Bandyopadhyay;Kishalay Das;M. Murty
通讯作者: S. Bandyopadhyay;Kishalay Das;M. Murty
DOI: 10.1109/tnsm.2021.3067775
发表时间: 2021-09
影响因子: 5.3
作者:
M. Pióro;M. Mycek;A. Tomaszewski
通讯作者: M. Pióro;M. Mycek;A. Tomaszewski
通过消息传递对网络进行拆解和顶点覆盖
DOI: 10.1109/tcsii.2020.2973414
发表时间: 2020
影响因子: 4.4
作者:
Dawei Zhao;Shumian Yang;Xiaohui Han;Shuhui Zhang;Zhen Wang
通讯作者: Zhen Wang
DOI: 10.1073/pnas.1800683115
发表时间: 2018-11-27
影响因子: 11.1
作者:
Benson, Austin R.;Abebe, Rediet;Kleinberg, Jon
通讯作者: Kleinberg, Jon
DOI: 10.24963/ijcai.2019/366
发表时间: 2019-08
期刊: --
影响因子: --
作者:
Jianwen Jiang;Yuxuan Wei;Yifan Feng;Jingxuan Cao;Yue Gao
通讯作者: Jianwen Jiang;Yuxuan Wei;Yifan Feng;Jingxuan Cao;Yue Gao