Nothing Else Matters: Model-Agnostic Explanations By Identifying Prediction Invariance
This work addresses the need for better interpretability in machine learning models, which is crucial for users who need to understand and trust model predictions, though it appears incremental as it builds on existing LIME methods.
The authors tackled the problem of interpretable machine learning by proposing anchor-LIME (aLIME), a model-agnostic technique that produces high-precision rule-based explanations with clear coverage boundaries, and demonstrated its flexibility across various domains and tasks.
At the core of interpretable machine learning is the question of whether humans are able to make accurate predictions about a model's behavior. Assumed in this question are three properties of the interpretable output: coverage, precision, and effort. Coverage refers to how often humans think they can predict the model's behavior, precision to how accurate humans are in those predictions, and effort is either the up-front effort required in interpreting the model, or the effort required to make predictions about a model's behavior. In this work, we propose anchor-LIME (aLIME), a model-agnostic technique that produces high-precision rule-based explanations for which the coverage boundaries are very clear. We compare aLIME to linear LIME with simulated experiments, and demonstrate the flexibility of aLIME with qualitative examples from a variety of domains and tasks.