Blocking Influence at Collective Level with Hard Constraints (Student Abstract)
Blocking Influence at Collective Level with Hard Constraints (Student Abstract)
复制标题
DOI：
10.1609/aaai.v36i11.21694
复制
发表时间：
2022-06
期刊：
影响因子：
--
通讯作者：
Zonghan Zhang;Subhodip Biswas;Fanglan Chen;Kaiqun Fu;Taoran Ji;Chang-Tien Lu;Naren Ramakrishnan;Zhiqian Chen
中科院分区：
文献类型：
--
作者：
Zonghan Zhang;Subhodip Biswas;Fanglan Chen;Kaiqun Fu;Taoran Ji;Chang-Tien Lu;Naren Ramakrishnan;Zhiqian Chen
影响阻断最大化（IBM）是许多关键的现实世界中的问题，如谣言预防和流行病遏制至关重要。现有的工作存在以下问题：（1）集中在个体水平上的统一成本，（2）主要利用贪婪方法来近似优化，（3）缺乏适当的图形表示用于影响估计。为了解决这些问题，本研究引入了一种称为神经影响阻塞（\algo）的神经网络模型，以改进近似和增强影响阻塞的有效性。该代码可在https://github.com/oates9895/NIB上获得。
Influence blocking maximization (IBM) is crucial in many critical real-world problems such as rumors prevention and epidemic containment. The existing work suffers from: (1) concentrating on uniform costs at the individual level, (2) mostly utilizing greedy approaches to approximate optimization, (3) lacking a proper graph representation for influence estimates. To address these issues, this research introduces a neural network model dubbed Neural Influence Blocking (\algo) for improved approximation and enhanced influence blocking effectiveness. The code is available at https://github.com/oates9895/NIB.