Open positions
Open research positions in SNAP group are available here.

Butterfly similarity network

Dataset information

This is a butterfly similarity network. Nodes represent butterflies (organisms) and edges represent visual similarities between the organisms. Visual similarities are calculated using butterfly images.


Dataset statistics
Nodes 832
Edges 86528
Nodes in largest SCC 832
Fraction of nodes in largest SCC 1.000000
Edges in largest SCC 86528
Fraction of edges in largest SCC 1.000000
Average clustering coefficient 0.595439
Number of triangles 14774008
Fraction of closed triangles 0.301405
Diameter (longest shortest path) 3
90-percentile effective diameter 1.918374

The information is extracted from the Leeds butterfly fine-grained species image dataset. Network statistics are calculated on edges with weights above the 75-th percentile.

References


Files

File Size Description
SS-Butterfly_labels.tsv.gz 17MB Butterfly species (labels)
SS-Butterfly_weights.tsv.gz 17MB Butterfly similarity network (weighted edgelist)