Keynote Speakers

Explainability and Fairness are the two emerging areas of research in artificial intelligence. When talking of explainability, the main emphasis remains on explaining the prediction itself, for example, how each feature contributes towards the overall predicted value. Whilst explaining the prediction is important, a little has been done on explaining the robustness of these models, that is, how each feature contributes towards achieving the model’s robustness. I will discuss how we can use Shapley values to decompose Receiver-operating Characteristics (ROC) curve and the Area under the ROC curve (AUC). With the help of an illustrative example, I will demonstrate the proposed idea and visualising the uncertainties in these curves. For imbalanced datasets, the use of Precision-Recall Curve (PRC) is considered more appropriate, therefore I will also demonstrate how to explain the PRCs with the help of Shapley values. The explanation of robustness can help analysts in a number of ways, for example, it can help in feature selection by identifying the irrelevant features that can be removed to reduce the computational complexity. It can also help in identifying the features having critical contributions or negative contributions towards robustness. I will conclude the talk by discussing the issue of fairness in these algorithms, and will mention some open areas to investigate in this domain.