Affiliation:
1. School of Engineering Mathematics and Technology, University of Bristol, Bristol BS8 1TR, UK
Abstract
(1) The enhanced capability of graph neural networks (GNNs) in unsupervised community detection of clustered nodes is attributed to their capacity to encode both the connectivity and feature information spaces of graphs. The identification of latent communities holds practical significance in various domains, from social networks to genomics. Current real-world performance benchmarks are perplexing due to the multitude of decisions influencing GNN evaluations for this task. (2) Three metrics are compared to assess the consistency of algorithm rankings in the presence of randomness. The consistency and quality of performance between the results under a hyperparameter optimisation with the default hyperparameters is evaluated. (3) The results compare hyperparameter optimisation with default hyperparameters, revealing a significant performance loss when neglecting hyperparameter investigation. A comparison of metrics indicates that ties in ranks can substantially alter the quantification of randomness. (4) Ensuring adherence to the same evaluation criteria may result in notable differences in the reported performance of methods for this task. The W randomness coefficient, based on the Wasserstein distance, is identified as providing the most robust assessment of randomness.
Subject
General Physics and Astronomy
Reference53 articles.
1. Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv.
2. Graph clustering;Schaeffer;Comput. Sci. Rev.,2007
3. Monti, F., Frasca, F., Eynard, D., Mannion, D., and Bronstein, M.M. (2019). Fake news detection on social media using geometric deep learning. arXiv.
4. Cabreros, I., Abbe, E., and Tsirigos, A. (2016, January 16–18). Detecting community structures in hi-c genomic data. Proceedings of the 2016 Annual Conference on Information Science and Systems (CISS), Princeton, NJ, USA.
5. Yang, J., McAuley, J., and Leskovec, J. (2013, January 7–10). Community detection in networks with node attributes. Proceedings of the 2013 IEEE 13th International Conference on Data Mining, Dallas, TX, USA.