Cinquini M., Giannotti F., Guidotti R., Mattei A.
Decision-making Missing data Explainable AI Data imputation Local post-hoc explanation Missing values
Missing data are quite common in real scenarios when using Artificial Intelligence (AI) systems for decision-making with tabular data and effectively handling them poses a significant challenge for such systems. While some machine learning models used by AI systems can tackle this problem, the existing literature lacks post-hoc explainability approaches able to deal with predictors that encounter missing data. In this paper, we extend a widely used local model-agnostic post-hoc explanation approach that enables explainability in the presence of missing values by incorporating state-of-the-art imputation methods within the explanation process. Since our proposal returns explanations in the form of feature importance, the user will be aware also of the importance of a missing value in a given record for a particular prediction. Extensive experiments show the effectiveness of the proposed method with respect to some baseline solutions relying on traditional data imputation.
Source: xAI 2023 - World Conference on Explainable Artificial Intelligence, pp. 256–278, Lisbon, Portugal, 26-28/07/2023
@inproceedings{oai:it.cnr:prodotti:490383, title = {Handling missing values in local post-hoc explainability}, author = {Cinquini M. and Giannotti F. and Guidotti R. and Mattei A.}, doi = {10.1007/978-3-031-44067-0_14}, booktitle = {xAI 2023 - World Conference on Explainable Artificial Intelligence, pp. 256–278, Lisbon, Portugal, 26-28/07/2023}, year = {2023} }
TAILOR
Foundations of Trustworthy AI - Integrating Reasoning, Learning and Optimization
XAI
Science and technology for the explanation of AI decision making
SoBigData-PlusPlus
SoBigData++: European Integrated Infrastructure for Social Mining and Big Data Analytics
Humane AI
Toward AI Systems That Augment and Empower Humans by Understanding Us, our Society and the World Around Us