Random walk was first introduced by Karl Pearson in 1905 and has inspired many research works in different fields. In recent years, random walk has been adopted in information network research, for example, ranking and similarity estimation. In this paper, we introduce a new model called RankCompete, which allows multiple random walkers in the same network (existing work mostly focus on random walks of a single category). By introducing the "competition" concept into the random walk framework, our method can fulfill both clustering and ranking tasks simultaneously and thus provide an effective analysis tool for networks. Compared with the traditional network ranking approaches, our new method focuses more on the structure of specialized clusters. Compared with the traditional graph clustering approaches, our new method provides a faster and more intuitive way to group the network nodes. We validate our approach on both bibliography networks and visual information networks, and the results show that our approach can obtain 100% perfect clustering results in clustering the DBLP 20 conferences and outperform the state-of-the-art on the Cora dataset. Furthermore, we show that our method can be effectively used to summarize personal photo collections.
- Information network
ASJC Scopus subject areas
- Computer Science Applications
- Cognitive Neuroscience
- Artificial Intelligence