Topic
Katz centrality
About: Katz centrality is a research topic. Over the lifetime, 601 publications have been published within this topic receiving 77858 citations.
Papers published on a yearly basis
Papers
More filters
••
03 Aug 2013TL;DR: A novel connectionist method which measures node centrality for directed and weighted networks, employing a spreading activation mechanism in order to measure the influence of a given node on the others, within an information diffusion circumstance.
Abstract: Identifying key nodes in networks, in terms of centrality measurement, is one of the popular research topics in network analysis. Various methods have been proposed with different interpretations of centrality. This paper proposes a novel connectionist method which measures node centrality for directed and weighted networks. The method employs a spreading activation mechanism in order to measure the influence of a given node on the others, within an information diffusion circumstance. The experimental results show that, compared with other popular centrality measurement methods, the proposed method performs the best for finding the most influential nodes.
2 citations
•
TL;DR: This paper presents and leverages a surprising relationship between Katz centrality and eigenvector centrality to detect communities and demonstrates that this approach identifies communities that are as good or better than conventional methods.
Abstract: The computational demands of community detection algorithms such as Louvain and spectral optimization can be prohibitive for large networks. Eigenvector centrality and Katz centrality are two network statistics commonly used to describe the relative importance of nodes; and their calculation can be closely approximated on large networks by scalable iterative methods. In this paper, we present and leverage a surprising relationship between Katz centrality and eigenvector centrality to detect communities. Beyond the computational gains, we demonstrate that our approach identifies communities that are as good or better than conventional methods.
2 citations
•
TL;DR: This paper constructs an algorithm that iteratively improves upper and lower bounds on the Katz score of a given node until a correct Katz ranking is obtained, and provides efficient parallel CPU and GPU implementations of the algorithm that enable near real-time Katz centrality computation for graphs with hundreds of millions of nodes in fractions of seconds.
Abstract: Network analysis defines a number of centrality measures to identify the most central nodes in a network. Fast computation of those measures is a major challenge in algorithmic network analysis. Aside from closeness and betweenness, Katz centrality is one of the established centrality measures. In this paper, we consider the problem of computing rankings for Katz centrality. In particular, we propose upper and lower bounds on the Katz score of a given node. While previous approaches relied on numerical approximation or heuristics to compute Katz centrality rankings, we construct an algorithm that iteratively improves those upper and lower bounds until a correct Katz ranking is obtained. We extend our algorithm to dynamic graphs while maintaining its correctness guarantees. Experiments demonstrate that our static graph algorithm outperforms both numerical approaches and heuristics with speedups between 1.5x and 3.5x, depending on the desired quality guarantees. Our dynamic graph algorithm improves upon the static algorithm for update batches of less than 10000 edges. We provide efficient parallel CPU and GPU implementations of our algorithms that enable near real-time Katz centrality computation for graphs with hundreds of millions of nodes in fractions of seconds.
2 citations
••
TL;DR: To measure the extent to which the distribution of workload between actors in the network can be equalized, a degree-weighted measure for a balanced workload based on betweenness centrality is introduced.
2 citations
••
04 Aug 2015TL;DR: A pseudo polynomial-time algorithm for temporal networks, of which the transit value is always positive and the least common divisor of all transit values is bounded, and shows that the centrality of networks with 125 nodes and 455 edges can be efficiently computed in 3.2 seconds.
Abstract: In this paper, we propose a clustering method based on the infinite betweenness centrality for temporal networks specified by 1-dimensional periodic graphs. While the temporal networks have a wide range of applications such as opportunistic communication, there are not many clustering algorithms specifically proposed for them. We give a pseudo polynomial-time algorithm for temporal networks, of which the transit value is always positive and the least common divisor of all transit values is bounded. Our experimental results show that the centrality of networks with 125 nodes and 455 edges can be efficiently computed in 3.2 seconds. Not only the clustering results using the infinite betweenness centrality for this kind of networks are better, but also the nodes with biggest influence are more precisely detected when the betweenness centrality is computed over the periodic graph.
2 citations