Temporal networks are an effective way to encode temporal information into graph data *** the bursting cohesive subgraph(BCS),which accumulates its cohesiveness at the fastest rate,is an important problem in temporal ...
详细信息
Temporal networks are an effective way to encode temporal information into graph data *** the bursting cohesive subgraph(BCS),which accumulates its cohesiveness at the fastest rate,is an important problem in temporal *** BCS has a large number of applications,such as representing emergency events in social media,traffic congestion in road networks and epidemic outbreak in ***,existing methods demand the BCS lasting for a time interval,which neglects the timeliness of the *** this paper,we design an early bursting cohesive subgraph(EBCS)model based on the k-core to enable identifying the burstiness as soon as *** find the EBCS,we first construct a time weight graph(TWG)to measure the bursting level by integrating the topological and temporal ***,we propose a global search algorithm,called GS-EBCS,which can find the exact EBCS by iteratively removing nodes from the ***,we propose a local search algorithm,named LS-EBCS,to find the EBCS by first expanding from a seed node until obtaining a candidate k-core and then refining the k-core to the result subgraph in an optimal time ***,considering the situation that the massive temporal networks cannot be completely put into the memory,we first design an i/o method to build the TWG and then develop i/oefficient global search and local search algorithms,namely i/o-GS and i/o-LS respectively,to find the EBCS under the semi-external *** experiments,conducted on four real temporal networks,demonstrate the efficiency and effectiveness of our proposed *** example,on the DBLP dataset,i/o-LS and LS-EBCS have comparable running time,while the maximum memory usage of i/o-LS is only 6.5 MB,which is much smaller than that of LS-EBCS taking 308.7 MB.
The problem of computing k-edge connected components ( k-ECCs) of a graph G for a specific k is a fundamental graph problem and has been investigated recently. in this paper, we study the problem of ECC decomposition,...
详细信息
The problem of computing k-edge connected components ( k-ECCs) of a graph G for a specific k is a fundamental graph problem and has been investigated recently. in this paper, we study the problem of ECC decomposition, which computes the k-ECCs of a graph G for all possible k values. ECC decomposition can be widely applied in a variety of applications such as graph-topology analysis, community detection, Steiner Component Search, and graph visualization. A straightforward solution for ECC decomposition is to apply the existing k-ECC computation algorithm to compute the k-ECCs for all k values. However, this solution is not applicable to large graphs for two challenging reasons. First, all existing k-ECC computation algorithms are highly memory intensive due to the complex data structures used in the algorithms. Second, the number of possible k values can be very large, resulting in a high computational cost when each k value is independently considered. in this paper, we address the above challenges, and study i/oefficient ECC decomposition via graph reduction. We introduce two elegant graph reduction operators which aim to reduce the size of the graph loaded in memory while preserving the connectivity information of a certain set of edges to be computed for a specific k. We also propose three novel i/o efficient algorithms, Bottom-Up, Top-Down, and Hybrid, that explore the k values in different orders to reduce the redundant computations between different k values. We analyze the i/o and memory costs for all proposed algorithms. in addition, we extend our algorithm to build an efficientindex for Steiner Component Search. We show that our index can be used to perform Steiner Component Search in optimal i/os when only the node information of the graph is allowed to be loaded in memory. in our experiments, we evaluate our algorithms using seven real large datasets with various graph properties, one of which contains 1.95 billion edges. The experimental results show t
暂无评论