Contributo in atti di convegno, 2019, ENG, 10.1109/IJCNN.2019.8852158

On the stability of interpretable models

Guidotti R.; Ruggieri S.

CNR-ISTI, Pisa, Italy; CNR-ISTI - University of Pisa, Pisa, Italy

Interpretable classification models are built with the purpose of providing a comprehensible description of the decision logic to an external oversight agent. When considered in isolation, a decision tree, a set of classification rules, or a linear model, are widely recognized as human-interpretable. However, such models are generated as part of a larger analytical process. Bias in data collection and preparation, or in model's construction may severely affect the accountability of the design process. We conduct an experimental study of the stability of interpretable models with respect to feature selection, instance selection, and model selection. Our conclusions should raise awareness and attention of the scientific community on the need of a stability impact assessment of interpretable models.

IJCNN 2019 - International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, 14-19 July, 2019

Keywords

Classifiers, Interpretability, Model Stability

CNR authors

Ruggieri Salvatore, Guidotti Riccardo

CNR institutes

ISTI – Istituto di scienza e tecnologie dell'informazione "Alessandro Faedo"

ID: 417416

Year: 2019

Type: Contributo in atti di convegno

Creation: 2020-02-20 14:45:56.000

Last update: 2021-01-12 22:24:24.000

External IDs

CNR OAI-PMH: oai:it.cnr:prodotti:417416

DOI: 10.1109/IJCNN.2019.8852158

Scopus: 2-s2.0-85073207373

ISI Web of Science (WOS): 000530893803090