Once you've generated or imported a Network Graph, Explainable AI (XAI) analyzes relationships that define each segment within a network and provides you with succinct descriptions of these insights.

XAI can help you better understand your Network Graph segments and promote further exploration. This additional context is critical to drive insights from network analysis.

Tip: XAI can be run on any type of network visualization within the platform, regardless of whether or not the Network Extractor was used to construct the network.

Running Explainable AI on a Network Graph

1. Click the XAI icon ( ) in the top toolbar to open the XAI panel.

2. Under Add Target, select the XAI method you would like to use:

   • Relative Edge Density (default) - This method will attempt to determine which characteristics are most descriptive for each segment. The descriptions in each result card may be interpreted as saying that if a node falls into Segment N, then it likely has certain values for the input features.

   • Identification Tree - This method will attempt to determine which characteristics are most specific to each segment. The descriptions in each result card may be interpreted as saying that if a node has certain values for the input features, then it likely falls into Segment N.

   • Komolgorov-Smirnov Test - The Kolmogorov–Smirnov test determines whether a segment has a statistically significantly different distribution for each numerical feature provided as input.

3. Select Segments in the target drop-down.

4. Add other features by choosing them from the Select Features drop-down or using the Input All button.

   Tip: If you used the Network Extractor to generate your network, try using your Associative Features as inputs here.

5. Click Run at the bottom of the panel.

The panel will populate with cards that describe the segments. Click the cards to explore which segments contain certain relationships.