ExplainReduce: Generating global explanations from many local explanations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914598293078016 |
|---|---|
| author | Seppäläinen, Lauri Guo, Mudong Puolamäki, Kai |
| author_facet | Seppäläinen, Lauri Guo, Mudong Puolamäki, Kai |
| contents | 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. We show that, for many problems, as few as five explanations can faithfully emulate the closed-box model and that our reduction procedure is competitive with other model aggregation methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_10311 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ExplainReduce: Generating global explanations from many local explanations Seppäläinen, Lauri Guo, Mudong Puolamäki, Kai Machine Learning Artificial Intelligence Human-Computer Interaction I.2.4 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. We show that, for many problems, as few as five explanations can faithfully emulate the closed-box model and that our reduction procedure is competitive with other model aggregation methods. |
| title | ExplainReduce: Generating global explanations from many local explanations |
| topic | Machine Learning Artificial Intelligence Human-Computer Interaction I.2.4 |
| url | https://arxiv.org/abs/2502.10311 |