Print Email Facebook Twitter A Study on Counterfactual Explanations Title A Study on Counterfactual Explanations: Investigating the impact of inter-class distance and data imbalance Author Zagorac, Ivor (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Liem, C.C.S. (mentor) Altmeyer, P. (mentor) Tax, D.M.J. (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science Date 2024-06-13 Abstract Counterfactual explanations (CEs) are emerging as a crucial tool in Explainable AI (XAI) for understanding model decisions. This research investigates the impact of various factors on the quality of CEs generated for classification tasks. We explore how inter-class distance, data imbalance, balancing techniques, the presence of biased classifiers, and decision thresholds influence CE quality. To answer these research questions, we conduct experiments on various datasets, classification models and counterfactual generators. The datasets include the MNIST and GMSC dataset. The models include well-established models like MLP and Random Forest, along with the novel NeuroTree model. The generators include the method proposed by Wachter et al. and the REVISE method. We evaluate how different factors affect CE quality by performing an extensive experimental analysis. Our findings demonstrate that increasing inter-class distance degrades CE quality, particularly explanation plausibility. Data imbalance showed minimal impact, while balancing techniques yielded a slight improvement in CE plausibility, especially for the minority class. Classifiers biased towards specific subgroups resulted in lower CE quality for those subgroups. We observed limited evidence for a consistent amplification effect of decision thresholds. This research utilizes various datasets and classification models, including the novel NeuroTree model. Our findings contribute to XAI by providing insights into factors affecting CE quality and highlighting areas for future development, particularly regarding fairness and handling imbalanced data. Subject Counterfactual ExplanationsXAIData Imbalance To reference this document use: http://resolver.tudelft.nl/uuid:6e2c240c-03c6-4e0e-af2c-5d257e77c77c Part of collection Student theses Document type master thesis Rights © 2024 Ivor Zagorac Files PDF Final_Thesis_Ivor_Zagorac.pdf 3.71 MB Close viewer /islandora/object/uuid:6e2c240c-03c6-4e0e-af2c-5d257e77c77c/datastream/OBJ/view