Konuşmacılar
İsmail Hakkı Toroslu
(Orta Doğu Teknik Üniversitesi)
Açıklama
Computing betweenness centrality (BC) in large graphs is crucial for various applications including telecommunications, social, and biological networks. However, the huge size of data presents significant challenges. In this paper, we introduce a novel approximate approach for efficiently extracting top-k BC nodes using a combination of Louvain community detection and Brandes’ algorithm. Our method significantly enhances the runtime efficiency of the traditional Brandes’ algorithm while
preserving accuracy across synthetic and real-world datasets. Additionally, our approach is suitable to parallelization, further improving its efficiency. Experimental results confirm the effectiveness of our method for large, sparse graphs.