CounterNet: End-to-End Training of Prediction Aware Counterfactual Explanations

Hangzhi Guo, Thanh Hong Nguyen, Amulya Yadav

Keywords: Counterfactual Explanation, Algorithmic Recourse, Explainable AI, Interpretability

Abstract: Counterfactual (or CF) explanations are a type of local explanations for Machine Learning (ML) model predictions, which offer a contrastive case as an explanation by finding the smallest changes (in feature space) to the input data point, which will lead to a different prediction by the ML model. Existing CF explanation techniques suffer from two major limitations: (i) all of them are post-hoc methods designed for use with proprietary ML models --- as a result, their procedure for generating CF explanations is uninformed by the training of the ML model, which leads to misalignment between model predictions and explanations; and (ii) most of them rely on solving separate time-intensive optimization problems to find CF explanations for each input data point (which negatively impacts their runtime). This work makes a novel departure from the prevalent post-hoc paradigm (of generating CF explanations) by presenting CounterNet, an end-to-end learning framework which integrates predictive model training and the generation of counterfactual (CF) explanations into a single pipeline. We adopt a block-wise coordinate descent procedure which helps in effectively training CounterNet's network. Our extensive experiments on multiple real-world datasets show that CounterNet generates high-quality predictions, and consistently achieves 100% CF validity and very low proximity scores (thereby achieving a well-balanced cost-invalidity trade-off) for any new input instance, and runs 3X faster than existing state-of-the-art baselines.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Social Aspects of Machine Learning (eg, AI safety, fairness, privacy, interpretability, human-AI interaction, ethics)