Navigating Explanatory Multiverse Through Counterfactual Path Geometry

원문 초록

Counterfactual explanations are the de facto standard when tasked with interpreting decisions of (opaque) predictive models. Their generation is often subject to algorithmic and domain-specific constraints -- such as density-based feasibility, and attribute (im)mutability or directionality of change -- that aim to maximise their real-life utility. In addition to desiderata with respect to the counterfactual instance itself, existence of a viable path connecting it with the factual data point, known as algorithmic recourse, has become an important technical consideration. While both of these requirements ensure that the steps of the journey as well as its destination are admissible, current literature neglects the multiplicity of such counterfactual paths. To address this shortcoming we introduce the novel concept of explanatory multiverse that encompasses all the possible counterfactual journeys. We then show how to navigate, reason about and compare the geometry of these trajectories with two methods: vector spaces and graphs. To this end, we overview their spacial properties -- such as affinity, branching, divergence and possible future convergence -- and propose an all-in-one metric, called opportunity potential, to quantify them. Implementing this (possibly interactive) explanatory process grants explainees agency by allowing them to select counterfactuals based on the properties of the journey leading to them in addition to their absolute differences. We show the flexibility, benefit and efficacy of such an approach through examples and quantitative evaluation on the German Credit and MNIST data sets.