One Node at a Time: Node-Level Network Classification
This work addresses network classification for researchers in network science, offering incremental insights by linking node-level patterns to whole-network classification.
The paper tackled the problem of network classification by exploring whether nodes from different network categories can be distinguished based on structural characteristics, and demonstrated that a classifier can accurately predict network category from individual nodes without seeing the entire network.
Network classification aims to group networks (or graphs) into distinct categories based on their structure. We study the connection between classification of a network and of its constituent nodes, and whether nodes from networks in different groups are distinguishable based on structural node characteristics such as centrality and clustering coefficient. We demonstrate, using various network datasets and random network models, that a classifier can be trained to accurately predict the network category of a given node (without seeing the whole network), implying that complex networks display distinct structural patterns even at the node level. Finally, we discuss two applications of node-level network classification: (i) whole-network classification from small samples of nodes, and (ii) network bootstrapping.