Structural identity is a concept of symmetry in which network nodes are identified according to the network structure and their relationship to other nodes. Structural identity has been studied in theory and practice over the past decades, but only recently has it been addressed with representational learning techniques. Numerical experiments indicate that state-of-the-art techniques for learning node representations fail in capturing stronger notions of structural identity, while struc2vec exhibits much superior performance in this task, as it overcomes limitations of prior approaches.
|Task||Dataset||Model||Metric name||Metric value||Global rank||Compare|
|Node Classification||BlogCatalog||Struc2vec||Accuracy||22.80%||# 2|
|Node Classification||BlogCatalog||Struc2vec||Macro-F1||0.216||# 2|
|Node Classification||Wikipedia||Struc2vec||Accuracy||21.10%||# 2|
|Node Classification||Wikipedia||Struc2vec||Macro-F1||0.190||# 2|