Efficient web matrix processing based on dual reordering

Chih-Ming Hsu, Ming-Syan Chen

Abstract: PageRank is one of the most important ranking techniques used in search engines nowadays. Since billions of pages already existed in Web, many PageRank acceleration techniques were explored by many researchers. However, in the real Web, just like the existence of pages without out-links, there are many pages without in-links. (In this paper, a Web page without in-links is called a reverse-dangling page.) Given the state of the art, we propose a new reordered PageRank algorithm, called two-way reordered PageRank algorithm, which exploits both dangling nodes and reverse-dangling nodes to reduce the computational complexity of the PageRank vector.