10 papers
UniFair: A unified fair clustering approach based on separation and compactness
Antonia Karra, Vasiliki Papanikou, Georgios Vardakas +2
Clustering is increasingly used to support high-impact decisions, yet standard objectives such as k-means can produce clusterings that treat demographic groups unequally. Existing…
TACENR: Task-Agnostic Contrastive Explanations for Node Representations
Vasiliki Papanikou, Evaggelia Pitoura
Graph representation learning has achieved notable success in encoding graph-structured data into latent vector spaces, enabling a wide range of downstream tasks. However, these no…
GALACTIC: Global and Local Agnostic Counterfactuals for Time-series Clustering
Christos Fragkathoulas, Eleni Psaroudaki, Themis Palpanas +1
Time-series clustering is a fundamental tool for pattern discovery, yet existing explainability methods, primarily based on feature attribution or metadata, fail to identify the tr…
EmeraldMind: A Knowledge Graph-Augmented Framework for Greenwashing Detection
Georgios Kaoukis, Ioannis Aris Koufopoulos, Eleni Psaroudaki +4
As AI and web agents become pervasive in decision-making, it is critical to design intelligent systems that not only support sustainability efforts but also guard against misinform…
FACEGroup: Feasible and Actionable Counterfactual Explanations for Group Fairness
Christos Fragkathoulas, Vasiliki Papanikou, Evaggelia Pitoura +1
Counterfactual explanations assess unfairness by revealing how inputs must change to achieve a desired outcome. This paper introduces the first graph-based framework for generating…
KGRAG-Ex: Explainable Retrieval-Augmented Generation with Knowledge Graph-based Perturbations
Georgios Balanos, Evangelos Chasanis, Konstantinos Skianis +1
Retrieval-Augmented Generation (RAG) enhances language models by grounding responses in external information, yet explainability remains a critical challenge, particularly when ret…