Link prediction based on path entropy
arXiv:1512.06348 · doi:10.1016/j.physa.2016.03.091
Abstract
Information theory has been taken as a prospective tool for quantifying the complexity of complex networks. In this paper, we first study the information entropy or uncertainty of a path using the information theory. Then we apply the path entropy to the link prediction problem in real-world networks. Specifically, we propose a new similarity index, namely Path Entropy (PE) index, which considers the information entropies of shortest paths between node pairs with penalization to long paths. Empirical experiments demonstrate that PE index outperforms the mainstream link predictors.
arXiv comment16 pages, 1 figure
References in corpus (34)
- Emergence of scaling in random networks
- Error and attack tolerance of complex networks
- Epidemic spreading in scale-free networks
- Assortative mixing in networks
- The structure of scientific collaboration networks
- Epidemic processes in complex networks
- Mixing patterns in networks
- Link Prediction in Complex Networks: A Survey
- Critical phenomena in complex networks
- Hierarchical structure and the prediction of missing links in networks
- Clustering and preferential attachment in growing networks
- Attack vulnerability of complex networks
- Predicting Missing Links via Local Information
- Self-similar community structure in organisations
- Vertex similarity in networks
- An information-theoretic framework for resolving community structure in complex networks
- Scale-Free Networks are Ultrasmall
- Effective and Efficient Similarity Index for Link Prediction of Complex Networks
- Link Prediction Based on Local Random Walk
- Deterministic Scale-Free Networks
- Highly clustered scale-free networks
- Entropy measures for complex networks: Toward an information theory of complex topologies
- Statistical Mechanics of Multiplex Ensembles: Entropy and Overlap
- The entropy of randomized network ensembles
- Reconstructing propagation networks with natural diversity and identifying hidden sources
- Epidemic spread in weighted scale-free networks
- Link prediction in complex networks: a local na\"ıve Bayes model
- Entropy Rate of Diffusion Processes on Complex Networks
- Link Prediction in Complex Networks: A Mutual Information Perspective
- Maximal-entropy random walks in complex networks with limited information
- Emergence of overlap in ensembles of spatial multiplexes and statistical mechanics of spatial interacting networks ensembles
- Understanding the internet topology evolution dynamics
- Epidemic spreading driven by biased random walks
- Traffic-driven epidemic spreading in correlated networks
Cited by in corpus (7)
- Reconstructing networks
- Entropy-based link prediction in weighted networks
- A comparative study of similarity-based and GNN-based link prediction approaches
- Maximal dispersion of adaptive random walks
- SimBins: An information-theoretic approach to link prediction in real multiplex networks
- Multiple predator based capture process on complex networks
- Node similarity distribution of complex networks and its application in link prediction