Experimental Design Based Method for Influence Maximization
Abstract— In this paper, we investigate the influence maximization problem on the independent cascade(IC)
model. An experimental design based algorithm is presented to find the seed set to maximize the influence in
social network. In the method, we consider each node in the social network as an experiment, and the
problem that choosing k seed nodes from the social network becomes that choosing the most representative k
trials from all trials. We also take the situation about the similar nodes into account and try to make the
similar nodes not as the seed at the same time. At last, we build the model and use the approach called
cross-iteration to solve the problem. Our experimental results show that this method can effectively select the
appropriate seed set to maximize the influence in the social network.
Index Terms— Social network, influence maximization, experimental design, cross-iteration
State Key Lab of Novel Software Tech, Nanjing University, CHINA
Department of Computer Science, Yangzhou University,CHINA
Cite: Yuliang Zhang, Ling Chen, "Experimental Design Based Method for Influence Maximization," Proceedings of 2019 the 9th International Workshop on Computer Science and Engineering, pp. 753-759, Hong Kong, 15-17 June, 2019.