7 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…
Composite Silhouette: A Subsampling-based Aggregation Strategy
Aggelos Semoglou, Aristidis Likas, John Pavlopoulos
Determining the number of clusters is a central challenge in unsupervised learning, where ground-truth labels are unavailable. The Silhouette coefficient is a widely used internal…
Silhouette-Driven Instance-Weighted -means
Aggelos Semoglou, Aristidis Likas, John Pavlopoulos
Clustering is a fundamental unsupervised learning task with applications across a wide range of domains. Popular algorithms such as -means are efficient and widely used, but can…
TopClustRAG at SIGIR 2025 LiveRAG Challenge
Juli Bakagianni, John Pavlopoulos, Aristidis Likas
We present TopClustRAG, a retrieval-augmented generation (RAG) system developed for the LiveRAG Challenge, which evaluates end-to-end question answering over large-scale web corpor…
Universal description of the Neutron Star's surface and its key global properties: A Machine Learning Approach for nonrotating and rapidly rotating stellar models
Grigorios Papigkiotis, Georgios Vardakas, Aristidis Likas +1
Neutron stars provide an ideal theoretical framework for exploring fundamental physics when nuclear matter surpasses densities encountered within atomic nuclei. Despite their param…
Counterfactual Explanations for k-means and Gaussian Clustering
Georgios Vardakas, Antonia Karra, Evaggelia Pitoura +1
Counterfactuals have been recognized as an effective approach to explain classifier decisions. Nevertheless, they have not yet been considered in the context of clustering. In this…