DeepAI AI Chat
Log In Sign Up

Formalising the Robustness of Counterfactual Explanations for Neural Networks

by   Junqi Jiang, et al.
Imperial College London

The use of counterfactual explanations (CFXs) is an increasingly popular explanation strategy for machine learning models. However, recent studies have shown that these explanations may not be robust to changes in the underlying model (e.g., following retraining), which raises questions about their reliability in real-world applications. Existing attempts towards solving this problem are heuristic, and the robustness to model changes of the resulting CFXs is evaluated with only a small number of retrained models, failing to provide exhaustive guarantees. To remedy this, we propose the first notion to formally and deterministically assess the robustness (to model changes) of CFXs for neural networks, that we call Δ-robustness. We introduce an abstraction framework based on interval neural networks to verify the Δ-robustness of CFXs against a possibly infinite set of changes to the model parameters, i.e., weights and biases. We then demonstrate the utility of this approach in two distinct ways. First, we analyse the Δ-robustness of a number of CFX generation methods from the literature and show that they unanimously host significant deficiencies in this regard. Second, we demonstrate how embedding Δ-robustness within existing methods can provide CFXs which are provably robust.


page 1

page 2

page 3

page 4


Robust Counterfactual Explanations for Random Forests

Counterfactual explanations describe how to modify a feature vector in o...

Robust Counterfactual Explanations for Tree-Based Ensembles

Counterfactual explanations inform ways to achieve a desired outcome fro...

Agree to Disagree: When Deep Learning Models With Identical Architectures Produce Distinct Explanations

Deep Learning of neural networks has progressively become more prominent...

A Series of Unfortunate Counterfactual Events: the Role of Time in Counterfactual Explanations

Counterfactual explanations are a prominent example of post-hoc interpre...

Counterfactual Plans under Distributional Ambiguity

Counterfactual explanations are attracting significant attention due to ...

Robust Explanation Constraints for Neural Networks

Post-hoc explanation methods are used with the intent of providing insig...

Unifying Model Explainability and Robustness via Machine-Checkable Concepts

As deep neural networks (DNNs) get adopted in an ever-increasing number ...