Categories
Publications

Preprint: “pygrank: A Python Package for Graphe Node Ranking”

Emmanouil Krasanakis 
Symeon Papadopoulos 
Ioannis Kompatsiaris
Centre for Research and Technology—Hellas

Andreas Symeonidis
Aristotle University of Thessaloniki

Abstract:

We introduce pygrank, an open-source Python package to define, run and evaluate node ranking algorithms. We provide object-oriented and extensively unit-tested algorithm components, such as graph filters, post-processors, measures, benchmarks and online tuning. Computations can be delegated to numpy, tensorflow or pytorch backends and fit in backpropagation pipelines. Classes can be combined to define interoperable complex algorithms. Within the context of this paper, we compare the package with related alternatives and demonstrate its flexibility and ease of use with code examples.

Keywords:

graph signal processing, node ranking, optimization