BSOGCN: Brain Storm Optimization Graph Convolutional Networks Based Heterogeneous Information Networks Embedding

Qu，Liang; Zhu，Huaisheng; Shi，Yuhui

10.1109/CEC48606.2020.9185532

2020-07-01

IEEE Congress on Evolutionary Computation (CEC) as part of the IEEE World Congress on Computational Intelligence (IEEE WCCI)

978-1-7281-6930-9

2020 IEEE Congress on Evolutionary Computation, CEC 2020 - Conference Proceedings

1-7

JUL 19-24, 2020

null,null,ELECTR NETWORK

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Recently, Graph Convolutional Networks (GCNs) have shown great potential in the field of graph embedding. They map the nodes of the graph into the low dimensional vectors by aggregating the neighbor nodes' features information. However, most existing GCNs only focus on the homogeneous information networks instead of the heterogeneous information networks (HINs) with multiple types of nodes which are more common in the real world. Because the different types of neighbor nodes could have different impacts on the target nodes, it is difficult to manually design a proper neighbor nodes' features information aggregating weights. To address this problem, we propose a novel HINs embedding algorithm based on the brain storm optimization (BSO) algorithm and the graph convolutional network (GCN), called BSOGCN, which utilizes BSO to optimize the neighbor nodes' features information aggregating weights. It can be applied to the various HINs under various scenarios without any prior knowledge. The proposed method has been evaluated on both inductive and transductive node multi-class classification tasks on three real-world HINs datasets. The experimental results demonstrate that BSOGCN is competitive against other state-of-the-art methods.

brain storm optimization graph convolutional networks graph embedding heterogeneous information networks

第一

英语

EI ; CPCI-S

National Key RD Program of China[2017YFC0804003]

Computer Science ; Engineering ; Mathematical & Computational Biology ; Operations Research & Management Science

Computer Science, Artificial Intelligence ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic ; Mathematical & Computational Biology ; Operations Research & Management Science

WOS:000703998200044

20204109316992

Graph theory ; Information services ; Graph structures ; Classification (of information) ; Graph neural networks ; Graph embeddings ; Convolution ; Convolutional neural networks

Precipitation:443.3 ; Information Theory and Signal Processing:716.1 ; Database Systems:723.3 ; Artificial Intelligence:723.4 ; Information Sources and Analysis:903.1 ; Information Services:903.4 ; Combinatorial Mathematics, Includes Graph Theory, Set Theory:921.4

2-s2.0-85092062644

Scopus

Southern University of Science and Technology,Department of Computer Science and Engineering,Shenzhen,China

Qu，Liang,Zhu，Huaisheng,Shi，Yuhui. BSOGCN: Brain Storm Optimization Graph Convolutional Networks Based Heterogeneous Information Networks Embedding[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2020:1-7.