Artificial benchmark for community detection with outliers (ABCD+o)

Abstract

AbstractThe Artificial Benchmark for Community Detection graph (ABCD) is a random graph model with community structure and power-law distribution for both degrees and community sizes. The model generates graphs with similar properties as the well-known LFR one, and its main parameter $$\xi$$ ξ can be tuned to mimic its counterpart in the LFR model, the mixing parameter $$\mu$$ μ . In this paper, we extend the ABCD model to include potential outliers. We perform some exploratory experiments on both the new ABCD+o model as well as a real-world network to show that outliers pose some distinguishable properties. This ensures that our new model may serve as a benchmark of outlier detection algorithms.