Reckoning with the Disagreement Problem: Explanation Consensus as a Training Objective
This addresses the need for trustworthy explanations in high-stakes neural network decisions, though it is incremental as it builds on existing explainer methods.
The paper tackles the disagreement problem among post hoc feature attribution explainers by introducing a training objective that improves explanation consensus, achieving improved consensus on unseen data across three datasets while examining the trade-off with model performance.
As neural networks increasingly make critical decisions in high-stakes settings, monitoring and explaining their behavior in an understandable and trustworthy manner is a necessity. One commonly used type of explainer is post hoc feature attribution, a family of methods for giving each feature in an input a score corresponding to its influence on a model's output. A major limitation of this family of explainers in practice is that they can disagree on which features are more important than others. Our contribution in this paper is a method of training models with this disagreement problem in mind. We do this by introducing a Post hoc Explainer Agreement Regularization (PEAR) loss term alongside the standard term corresponding to accuracy, an additional term that measures the difference in feature attribution between a pair of explainers. We observe on three datasets that we can train a model with this loss term to improve explanation consensus on unseen data, and see improved consensus between explainers other than those used in the loss term. We examine the trade-off between improved consensus and model performance. And finally, we study the influence our method has on feature attribution explanations.