Open positions
Open research positions in SNAP group are available at undergraduate, graduate and postdoctoral levels.

Deezer Europe Social Network

Dataset information

A social network of Deezer users which was collected from the public API in March 2020. Nodes are Deezer users from European countries and edges are mutual follower relationships between them. The vertex features are extracted based on the artists liked by the users. The task related to the graph is binary node classification - one has to predict the gender of users. This target feature was derived from the name field for each user.

FEATHER paper: arxiv.org
FEATHER project: Github


Dataset statistics
Directed No.
Node features Yes.
Edge features No.
Node labels Yes. Binary class.
Temporal No.
Nodes 28,281
Edges 92,752
Density 0.0002
Transitvity 0.0959

Possible tasks
Binary node classification
Link prediction
Community detection
Network visualization

Source (citation)

  • B. Rozemberczki and R. Sarkar. Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models. 2020.
  •          @misc{rozemberczki2020characteristic,
                   title={Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models},
                   author={Benedek Rozemberczki and Rik Sarkar},
                   year={2020},
                   eprint={2005.07959},
                   archivePrefix={arXiv},
                   primaryClass={cs.LG}
            }
            

    Files

    File Description
    deezer_europe.zip Deezer Europe Social Network