Dear all BigInsighters,

You are hereby invited to a new Explaining AI seminar. The seminar will be a webinar, since the speaker speaks all the way from Germany.

Speaker: Julia Herbinger (Ludwig-Maximilians-Universität München)

Location: Click here to join the meeting (Microsoft Teams)

Title: Decomposing Global Feature Effects Based on Feature Interactions

Abstract: Global feature effect methods, such as partial dependence (PD) plots, provide an intelligible visualization of the expected marginal feature effect. However, such global feature effect methods can be misleading, as they do not represent local feature effects of single observations well when feature interactions are present. In this talk, I will introduce a new framework called generalized additive decomposition of global effects (GADGET), which is based on recursive partitioning to find interpretable regions in the feature space such that the interaction-related heterogeneity of local feature effects is minimized. I will demonstrate its applicability to the most popular methods to visualize marginal feature effects, namely PD, accumulated local effects (ALE), and Shapley additive explanations (SHAP) dependence. Additionally, I will show that different measures to quantify and analyze feature interactions can be derived when GADGET is applied. To define the interacting feature subset for GADGET, I will introduce PINT, a novel permutation-based significance test to detect global feature interactions that is applicable to any feature effect method used within GADGET. I will demonstrate the applicability of the proposed methods based on simulation and real-world examples.

Welcome!