TODO: summarize from https://blog.derwen.ai/graph-levels-of-detail-ea4226abba55
Graph topological transform approaches so far (e.g.,
lee2023ingram) have focused on using relation affinities to train representation learning models. this may be another example of using deep learning as a mêlée weapon. instead,
results computed from graph of relations analysis naturally feed into statistical relational learning approaches such as probabilistic soft logic, to develop rule sets and ground truth for training SRE models.
TODO: survey/compare topological decomposition of graphs, then using statistics to determine how to reconstruct probabilistically => for recomposition of generate graph elements (not simple nodes, edges)