Interactive Visual Analysis on Large Attributed Networks

Increasing scale leaves a challenging problem for visualizing large attributed networks. Hierarchical aggregation is a promising solution. Existing methods mainly focus on the topological structure but ignore vertex properties; moreover, the inherent hierarchy restricts network navigation process. This paper proposes an user-specified visualization method with a content-based clustering algorithm to explore large attributed networks. The content-based algorithm is able to locate major structures and cluster network based on structural and attribute similarities. Then a novel visualization system is introduced that allows navigation of large networks at any level-of-detail. The user-specified interaction strategy enables user to manipulate cluster metrics and built hierarchy based on interest. Case study demonstrates that the proposed method is effective to extract global knowledge about the network as well as locate critical nodes and major structures.