Adapting to Change: Robust Counterfactual Explanations in Dynamic Data Landscapes

TL;DR

This paper presents DyGRACE, a semi-supervised graph-based method for generating robust counterfactual explanations in dynamic data environments, effectively handling distributional drift without relying on outdated decision functions.

Contribution

It introduces a novel semi-supervised graph autoencoder approach that adapts to changing data distributions for counterfactual explanation generation.

Findings

DyGRACE effectively detects distributional drift.

It generates robust counterfactuals without relying on the black-box oracle.

The method improves explanation stability over time.

Abstract

We introduce a novel semi-supervised Graph Counterfactual Explainer (GCE) methodology, Dynamic GRAph Counterfactual Explainer (DyGRACE). It leverages initial knowledge about the data distribution to search for valid counterfactuals while avoiding using information from potentially outdated decision functions in subsequent time steps. Employing two graph autoencoders (GAEs), DyGRACE learns the representation of each class in a binary classification scenario. The GAEs minimise the reconstruction error between the original graph and its learned representation during training. The method involves (i) optimising a parametric density function (implemented as a logistic regression function) to identify counterfactuals by maximising the factual autoencoder's reconstruction error, (ii) minimising the counterfactual autoencoder's error, and (iii) maximising the similarity between the factual and counterfactual graphs. This semi-supervised approach is independent of an underlying black-box oracle. A logistic regression model is trained on a set of graph pairs to learn weights that aid in finding counterfactuals. At inference, for each unseen graph, the logistic regressor identifies the best counterfactual candidate using these learned weights, while the GAEs can be iteratively updated to represent the continual adaptation of the learned graph representation over iterations. DyGRACE is quite effective and can act as a drift detector, identifying distributional drift based on differences in reconstruction errors between iterations. It avoids reliance on the oracle's predictions in successive iterations, thereby increasing the efficiency of counterfactual discovery. DyGRACE, with its capacity for contrastive learning and drift detection, will offer new avenues for semi-supervised learning and explanation generation.