Dynamic Parameter Selection for Community Detection Algorithms (Graph Networks)

In the pattern of life problem space, data is often represented via mathematical graphs, in which a variety of algorithms may be employed to conduct semi-autonomous analysis. While successful empirical application of graph-domain algorithms on ABI problems has been achieved, most of these algorithms require a tuning parameter, which is often set heuristically in real-world scenarios. Arete has developed a unique mathematical approach to dramatically reduce the human time required in graph-based intelligence systems based on recent advances in graph homology and topological data analysis (TDA). Our method dynamically and automatically perform parameter selection for graph-based algorithms, is extensible to any machine-readable dataset/algorithm pair, and dramatically improves the computational efficiency of  graph-based algorithms by exploiting their underlying mathematical properties.