ExplainReduce: Summarising local explanations via proxies
This work addresses the challenge of making black-box machine learning models more interpretable for users by providing a concise global summary from local explanations, though it appears incremental as it builds on existing local explanation methods like LIME and SHAP.
The paper tackles the problem of summarizing many local explanations from complex models by reducing them to a small set of proxy models, which serve as a generative global explanation, and presents ExplainReduce as an efficient optimization-based method for this reduction.
Most commonly used non-linear machine learning methods are closed-box models, uninterpretable to humans. The field of explainable artificial intelligence (XAI) aims to develop tools to examine the inner workings of these closed boxes. An often-used model-agnostic approach to XAI involves using simple models as local approximations to produce so-called local explanations; examples of this approach include LIME, SHAP, and SLISEMAP. This paper shows how a large set of local explanations can be reduced to a small "proxy set" of simple models, which can act as a generative global explanation. This reduction procedure, ExplainReduce, can be formulated as an optimisation problem and approximated efficiently using greedy heuristics.