Subscribe
Issue No.01  Jan. (2014 vol.25)
pp: 136145
Xiaodong Liu , Sch. of Comput., Nat. Univ. of Defense Technol., Changsha, China
Mo Li , Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, Singapore
Shanshan Li , Sch. of Comput., Nat. Univ. of Defense Technol., Changsha, China
Shaoliang Peng , Sch. of Comput., Nat. Univ. of Defense Technol., Changsha, China
Xiangke Liao , Sch. of Comput., Nat. Univ. of Defense Technol., Changsha, China
Xiaopei Lu , Sch. of Comput., Nat. Univ. of Defense Technol., Changsha, China
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPDS.2013.41
ABSTRACT
Influence Maximization aims to find the top$(K)$ influential individuals to maximize the influence spread within a social network, which remains an important yet challenging problem. Proven to be NPhard, the influence maximization problem attracts tremendous studies. Though there exist basic greedy algorithms which may provide good approximation to optimal result, they mainly suffer from low computational efficiency and excessively long execution time, limiting the application to largescale social networks. In this paper, we present IMGPU, a novel framework to accelerate the influence maximization by leveraging the parallel processing capability of graphics processing unit (GPU). We first improve the existing greedy algorithms and design a bottomup traversal algorithm with GPU implementation, which contains inherent parallelism. To best fit the proposed influence maximization algorithm with the GPU architecture, we further develop an adaptive Klevel combination method to maximize the parallelism and reorganize the influence graph to minimize the potential divergence. We carry out comprehensive experiments with both realworld and sythetic social network traces and demonstrate that with IMGPU framework, we are able to outperform the stateoftheart influence maximization algorithm up to a factor of 60, and show potential to scale up to extraordinarily largescale networks.
INDEX TERMS
Graphics processing units, Social network services, Parallel processing, Acceleration, Instruction sets, Computational modeling, Accuracy,bottomup traversal algorithm, Influence maximization, GPU, largescale social networks, IMGPU
CITATION
Xiaodong Liu, Mo Li, Shanshan Li, Shaoliang Peng, Xiangke Liao, Xiaopei Lu, "IMGPU: GPUAccelerated Influence Maximization in LargeScale Social Networks", IEEE Transactions on Parallel & Distributed Systems, vol.25, no. 1, pp. 136145, Jan. 2014, doi:10.1109/TPDS.2013.41
REFERENCES
