GLEAMS: Bridging the Gap Between Local and Global Explanations
This addresses the explainability gap for users needing both local and global insights in ML, though it appears incremental by combining existing concepts.
The paper tackled the problem of providing both local and global explanations for machine learning models by proposing GLEAMS, which partitions the input space and learns interpretable models in each sub-region, resulting in faithful surrogates and human-understandable insights as demonstrated on synthetic and real-world data.
The explainability of machine learning algorithms is crucial, and numerous methods have emerged recently. Local, post-hoc methods assign an attribution score to each feature, indicating its importance for the prediction. However, these methods require recalculating explanations for each example. On the other side, while there exist global approaches they often produce explanations that are either overly simplistic and unreliable or excessively complex. To bridge this gap, we propose GLEAMS, a novel method that partitions the input space and learns an interpretable model within each sub-region, thereby providing both faithful local and global surrogates. We demonstrate GLEAMS' effectiveness on both synthetic and real-world data, highlighting its desirable properties and human-understandable insights.