Centre for Research and Technology Hellas, 57001 Thermi, Thessaloniki, Greece; Aristotle University of Thessaloniki, 54124, Thessaloniki, Greece; Corresponding author at: Centre for Research and Technology Hellas, 57001 Thermi, Thessaloniki, Greece.
Symeon Papadopoulos
Centre for Research and Technology Hellas, 57001 Thermi, Thessaloniki, Greece
Ioannis Kompatsiaris
Centre for Research and Technology Hellas, 57001 Thermi, Thessaloniki, Greece
Andreas L. Symeonidis
Aristotle University of Thessaloniki, 54124, Thessaloniki, Greece
We introduce pygrank, an open source Python package to define, run and evaluate node ranking algorithms. We provide object-oriented and extensively unit-tested algorithmic 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 back-propagation pipelines. Classes can be combined to define interoperable complex algorithms. Within the context of this paper, we compare the package with related alternatives, describe its architecture, demonstrate its flexibility and ease of use with code examples, and discuss its impact.
