Marginalizing over the PageRank Damping Factor

TL;DR

This paper introduces TotalRank, a parameter-free version of PageRank obtained by marginalizing over the damping factor, with implications for information retrieval and classification.

Contribution

It presents a method to marginalize the damping parameter in PageRank, resulting in TotalRank, a novel parameter-free ranking algorithm.

Findings

TotalRank eliminates the need for damping parameter tuning.

The approach has applications in information retrieval.

It provides a new perspective on ranking algorithms.

Abstract

In this note, we show how to marginalize over the damping parameter of the PageRank equation so as to obtain a parameter-free version known as TotalRank. Our discussion is meant as a reference and intended to provide a guided tour towards an interesting result that has applications in information retrieval and classification.