Statistical reliability and path diversity based PageRank algorithm improvements
This work addresses ranking accuracy in web search or graph analysis, but it appears incremental as it builds on the original PageRank without claiming major breakthroughs.
The paper tackles the problem of improving the PageRank algorithm by introducing statistical reliability evaluation and path diversity, demonstrating their impact through examples and simulations.
In this paper we present new improvement ideas of the original PageRank algorithm. The first idea is to introduce an evaluation of the statistical reliability of the ranking score of each node based on the local graph property and the second one is to introduce the notion of the path diversity. The path diversity can be exploited to dynamically modify the increment value of each node in the random surfer model or to dynamically adapt the damping factor. We illustrate the impact of such modifications through examples and simple simulations.