Affiliation:
1. Tokyo Institute of Technology, Meguro, Tokyo, Japan
2. AIRC, AIST, Koto-ku, Tokyo, Japan
Abstract
Graphs arise naturally in numerous situations, including social graphs, transportation graphs, web graphs, protein graphs, etc. One of the important problems in these settings is to identify which nodes are important in the graph and how they affect the graph structure as a whole. Betweenness centrality and closeness centrality are two commonly used node ranking measures to find out influential nodes in the graphs in terms of information spread and connectivity. Both of these are considered as shortest path based measures as the calculations require the assumption that the information flows between the nodes via the shortest paths. However, exact calculations of these centrality measures are computationally expensive and prohibitive, especially for large graphs. Although researchers have proposed approximation methods, they are either less efficient or suboptimal or both. We propose the first graph neural network (GNN) based model to approximate betweenness and closeness centrality. In GNN, each node aggregates features of the nodes in multihop neighborhood. We use this feature aggregation scheme to model paths and learn how many nodes are reachable to a specific node. We demonstrate that our approach significantly outperforms current techniques while taking less amount of time through extensive experiments on a series of synthetic and real-world datasets. A benefit of our approach is that the model is inductive, which means it can be trained on one set of graphs and evaluated on another set of graphs with varying structures. Thus, the model is useful for both static graphs and dynamic graphs.
Source code is available at https://github.com/sunilkmaurya/GNN_Ranking
Funder
JSPS Grant-In-Aid for Scientific Research
JST CREST
JSPS Grant-In-Aid for Early-Career Scientists
The New Energy and Industrial Technology Development Organization
Publisher
Association for Computing Machinery (ACM)
Reference76 articles.
1. Communication Patterns in Task‐Oriented Groups
2. A mathematical model for group structures;Bavelas Alex;Applied Anthropology,1948
3. An improved index of centrality
4. Rianne van den Berg Thomas Kipf and Max Welling. 2017. Graph convolutional matrix completion. arXiv:1706.02263. Retrieved from https://arxiv.org/abs/1706.02263 Rianne van den Berg Thomas Kipf and Max Welling. 2017. Graph convolutional matrix completion. arXiv:1706.02263. Retrieved from https://arxiv.org/abs/1706.02263
Cited by
18 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献