Doctoral defence: Marharyta Domnich "Advancing human-centric counterfactual explanations in explainable AI“

On 15 January at 12:15 Marharyta Domnich will defend her doctoral thesis "Advancing human-centric counterfactual explanations in explainable AI“ to obtain the degree of Doctor of Philosophy (in Computer Science).

Supervisors:
Prof. Raul Vicente Zafra, University of Tartu
Research Fellow Eduard Barbu, University of Tartu

Opponents:
Prof. Barbara Hammer, Bielefeld University (Germany)
Assoc. Prof. Luca Longo, University College Cork (Ireland)

Summary
Artificial Intelligence increasingly influences critical decisions across diverse domains like healthcare, education, and finance. The growing complexity and scale of these models often make their decision-making processes opaque, highlighting the importance of developing explanation methods that enhance transparency and accountability. The field of Explainable AI (XAI) aims to address this challenge by developing explanations that are meaningful to users. Human explanation processes are inherently complex and contrastive, often involving comparisons and hypothetical scenarios. This contrastive way of thinking is captured effectively by counterfactual explanations, which answer the question, "What minimal changes could alter a model’s decision?". For counterfactual explanations to be effective, they must align closely with human preferences, ensuring they are meaningful, actionable, and trusted by users.

This thesis advances human-centric counterfactual explanations through four interconnected studies. By integrating insights from cognitive science, the research enhances both the generation and evaluation of counterfactual explanations across various domains.

The first study, inspired by human cognitive preferences, proposes the use of diffusion distance and directional coherence to enhance the search for counterfactual explanations. These innovations result in more feasible, human-centric explanations by emphasizing data connectivity and aligning changes in feature space with human reasoning patterns. Our approach, named Coherent Directional Counterfactual Explainer (CoDiCE), shows better performance in generating explanations that are both actionable and aligned with human explanatory virtues.

Addressing the critical issue of evaluating counterfactual explanations, the second study develops the CounterEval dataset, capturing detailed human judgments across multiple explanatory dimensions. Using data collected from over 200 participants, we introduce a unified evaluation framework that incorporates Large Language Models (LLMs) to predict averaged and individual human ratings, providing a scalable and consistent method to evaluate explanation quality. A subsequent analysis examines how perceived satisfaction with explanations can be modeled from other explanatory metrics (such as feasibility, trust, completeness, and complexity), providing deeper insights into the factors driving overall user satisfaction.

The practical impact of counterfactual explanations is further demonstrated in the context of medical imaging by introducing a COunterfactual INpainting approach (COIN) for weakly supervised semantic segmentation in medical imaging. COIN generates explanations by flipping classification outcomes from abnormal to normal, using the differences between the original and altered images as weak segmentation labels. Applied to kidney tumor segmentation, this methodology significantly reduces the manual labeling workload for radiologists and enables pathology segmentation in scenarios lacking extensively annotated datasets. Counterfactual inpainting significantly outperforms attribution-based methods, showcasing the real-world potential of counterfactual explanations in healthcare.

Together, these studies contribute to the field of XAI by developing and validating counterfactual explanation methods that enhance the transparency and usability of AI systems and also closely align with human cognitive processes.

The defence will be held also in Zoom (Meeting ID: 912 4308 5784, password: ati).