Bipartite graph capsule network

Abstract

Graphs have been widely adopted in various fields, where many graph models are developed. Most of previous research focuses on unipartite or homogeneous graph analysis. In this graphs, the relationships between the same type of entities are preserved in the graphs. Meanwhile, the bipartite graphs that model the complex relationships among different entities with vertices partitioned into two disjoint sets, are becoming increasing popular and ubiquitous in many real life applications. Though several graph classification methods on unipartite and homogenous graphs have been proposed by using kernel method, graph neural network, etc. However, these methods are unable to effectively capture the hidden information in bipartite graphs. In this paper, we propose the first bipartite graph-based capsule network, namely Bipartite Capsule Graph Neural Network (BCGNN), for the bipartite graph classification task. BCGNN exploits the capsule network and obtains information between the same type vertices in the bipartite graphs by constructing the one-mode projection. Extensive experiments are conducted on real-world datasets to demonstrate the effectiveness of our proposed method.

FPGN: follower prediction framework for infectious disease prevention

“…These approaches have been used in various applications such as social network analysis, protein function prediction, and knowledge graph completion [43]. In addition, there are some GNN models that have been specifically optimized for bipartite graph problems [54,56,57]. However, these methods cannot utilize temporal information and are therefore not suitable for application on temporal bipartite graphs.…”

A new logic circuits optimization algorithm using bipartite graph

“…The discrepancy between the size of N 1 and N 2 and the direction of the relationships, edges, between the nodes of the two sets only, approximate the execution time of matching and traversing a bipartite graph closer to the linear time in most circumstances [17]. There are unlimited number of applications for bipartite graph such as search engines, social networks [18], and recommendation systems [19], data and networks classification [20], [21], cloud computing [22], health care, biology and medicine [23]. Other applications relevant to bipartite graphs are related to x-ray crystallography, metabolic pathways, chemical reaction networks, missile guidance, routing and wavelength assignment problem, and metabolic pathways [24], [25],…”