pygrank: A Python Package for Graph Node Ranking

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.

[1]  Cesare Alippi,et al.  Graph Neural Networks in TensorFlow and Keras with Spektral , 2020, IEEE Comput. Intell. Mag..

[2]  Stephan Günnemann,et al.  Predict then Propagate: Graph Neural Networks meet Personalized PageRank , 2018, ICLR.

[3]  Yiannis Kompatsiaris,et al.  Prior Signal Editing for Graph Filter Posterior Fairness Constraints , 2021, ArXiv.

[4]  Yiannis Kompatsiaris,et al.  Unsupervised evaluation of multiple node ranks by reconstructing local structures , 2020, Applied Network Science.

[5]  Fan Chung Graham,et al.  Local Partitioning for Directed Graphs Using PageRank , 2007, Internet Math..

[6]  Pierre Vandergheynst,et al.  Graph Signal Processing: Overview, Challenges, and Applications , 2017, Proceedings of the IEEE.

[7]  Qian Huang,et al.  Combining Label Propagation and Simple Models Out-performs Graph Neural Networks , 2020, ICLR.

[8]  Aric Hagberg,et al.  Exploring Network Structure, Dynamics, and Function using NetworkX , 2008, Proceedings of the Python in Science Conference.

[9]  Hang Zhang,et al.  AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data , 2020, ArXiv.

[10]  Y. Kompatsiaris,et al.  Stopping Personalized PageRank without an Error Tolerance Parameter , 2020, 2020 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[11]  Jan Eric Lenssen,et al.  Fast Graph Representation Learning with PyTorch Geometric , 2019, ArXiv.

[12]  Symeon Papadopoulos,et al.  Boosted seed oversampling for local community ranking , 2020, Inf. Process. Manag..

[13]  Alex Smola,et al.  Deep Graph Library: Towards Efficient and Scalable Deep Learning on Graphs , 2019, ArXiv.

[14]  Rada Mihalcea,et al.  TextRank: Bringing Order into Text , 2004, EMNLP.