barkincavdaroglu / Link-Prediction-Mesh-Network

PyTorch Implementation of a Deep Learning Model for Temporal Link Prediction in MANETs
2 stars 1 forks source link

Data Analysis and Preprocessing #7

Closed barkincavdaroglu closed 1 year ago

barkincavdaroglu commented 1 year ago

Meshnet dataset

Distribution of "Closeness Vitality" (per node feature) - close to normal

Screenshot 2022-12-30 at 17 20 08

Distribution "Degree" (per node feature) - needs normalization

Screenshot 2022-12-30 at 17 21 13

Distribution of "Information Centrality" (per node feature) could benefit from further normalization

Screenshot 2022-12-30 at 17 21 41

Distribution of "Betweenness Centrality" (per node feature) requires normalization

Screenshot 2022-12-30 at 17 22 14

Distribution of "Average Neighbor Degree" (per node feature) no further preprocessing required

Screenshot 2022-12-30 at 17 22 41

The other 2 features, namely "is_articulation_point" and "is_in_barycenter" are binary, and the former is 0 for all nodes.

Distribution of "Weight" (per edge feature) which characterizes 1 - sigmoid(x) of initial weight x requires normalization

Screenshot 2022-12-30 at 17 24 58

Distribution of "Edge Betweenness" (per edge feature) requires normalization

Screenshot 2022-12-30 at 17 27 33