Detection

This tab displays the structure of the model inputted into the generated Experiment . It shows a directed graph where each layer is represented as a node and each connection as an edge.

Local Explanation

This tab allows users to select a local instance for the generated Experiment , automatically generate explanations, and perform evaluation and validation. It automatically classifies the available XAI (Explainable AI) methods for the input model and provides a UI for users to select the necessary methods.

The usage steps are as follows:

• Select an input from the Input Data Gallery .
• In the Explainers section, open the dropdown to select a Default parameter or click the Optimize button to perform hyperparameter optimization, and then select the Optimized parameter to use the corresponding XAI method.
• In the Evaluators section, choose a metric to evaluate the XAI.
• Click the Explain button.

The explanation results for the selected XAI methods will be displayed and sorted in order of the selected metric's results.

*Demo server is fixed to use 'AbPC' metric as an object of the optimization and ranking.