arXiv subjects

Georgios Vardakas

Publications and source records attributed to Georgios Vardakas.

9 recordsLinked to original sources

arXiv2026

UniFair: A unified fair clustering approach based on separation and compactness

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 fair clustering methods typically optimize a single notion of fairness and often overlook how clustering costs interact with the geometry of the induced decision boundaries. We propose UniFair, a unified framework that jointly optimizes separation fairness and social fairness. Separation fairness encourages protected groups to lie farther from the induced decision boundaries, while social fairness reduces disparities in within-cluster distortion by penalizing group-wise clustering costs. We develop gradient-based optimization procedures for separation-fair and unified k-means objectives, and extend them to deep clustering by enforcing the same criteria in the latent space of an autoencoder. Experiments on tabular and image datasets show that UniFair reduces both boundary-related and cost-based group disparities with only a modest increase in clustering loss.

cs.LG↗

arXiv2026

GW-FALCON: A Novel Feature-Driven Deep Learning Approach for Early Warning Alerts of BNS and NSBH Inspirals in Next-Generation GW Observatories

Next-generation GW observatories such as the ET and CE will detect BNS and NSBH inspirals with high SNRs and long in-band durations, making systematic early-warning alerts both feasible and scientifically valuable. Such triggers are essential for coordinating rapid electromagnetic follow-up. In this work, we introduce GW-FALCON, a novel feature-driven DL framework for early-time detection between GW signal+noise and noise-only data in next-generation detectors. Instead of feeding raw time series to CNN or more complex neural network architectures, we first extract a large set of statistical, temporal, and spectral quantities from short observational time windows using the TSFEL library. The resulting fixed-length feature vectors are then used as input to feed-forward ANNs suitable for low-latency operation. We demonstrate the method using simulated BNS and NSBH inspiral waveforms injected into colored Gaussian noise generated from the ET and CE design PSDs. We train separate ANNs on feature sets extracted from partial-inspiral windows characterized by different maximum instantaneous frequencies, enabling early-warning triggers from tens to hundreds of seconds before merger. Across all detector configurations and datasets, the resulting classifiers achieve high accuracy and detection efficiency, with ET-like networks typically reaching test accuracies of order 90% and CE-like ones exceeding 97% at low false-alarm probability. To the best of our knowledge, this work presents the first comprehensive feature-based DL detection framework for Next-generation GW observatories, connecting feature extraction from strain time series data to robust signal-noise classification within a setup that can be extended to real data and to more advanced neural network architectures.

astro-ph.IM↗

arXiv2025

Assessing Universal Relations for Rapidly Rotating Neutron Stars: Insights from an Interpretable Deep Learning Perspective

Relations between stellar properties independent of the nuclear equation of state offer profound insights into neutron star physics and have practical applications in data analysis. Commonly, these relations are derived from utilizing various realistic nuclear cold hadronic, hyperonic, and hybrid EoS models, each of which should obey the current constraints and cover a wide range of stiffnesses. Concurrently, the field of multimessenger astronomy has been significantly enhanced by the advent of gravitational wave astronomy, which increasingly incorporates deep learning techniques and algorithms. At the same time, X-ray spectral data from NICER based on known pulsars are available, and additional observations are expected from upcoming missions. In this study, we revisit established universal relations, introduce new ones, and reassess them using a feed-forward neural network as a regression model. More specifically, we mainly propose ``deep'' EoS-insensitive hypersurface relations for rapidly rotating compact objects between several of the star's global parameters, which achieve an accuracy of within $1\%$ in most cases, with only a small fraction of investigated models exceeding this threshold. While analytical expressions can be used to represent some of these relations, the neural network approach demonstrates superior performance, particularly in complex regions of the parameter space. Furthermore, we use the SHapley Additive exPlanations (SHAP) method to interpret the suggested network's predictions, since is based on a strong theoretical framework inspired by the field of cooperative Game Theory. Most importantly, these highly accurate universal relations empowered with the interpretability description could be used in efforts to constrain the high-density equation of state in neutron stars, with the potential to enhance our understanding as new observables emerge.

astro-ph.HE↗

arXiv2025

Universal description of the Neutron Star's surface and its key global properties: A Machine Learning Approach for nonrotating and rapidly rotating stellar models

Neutron stars provide an ideal theoretical framework for exploring fundamental physics when nuclear matter surpasses densities encountered within atomic nuclei. Despite their paramount importance, uncertainties in the equation of state (EoS) have shrouded their internal structure. For rotating neutron stars, the shape of their surface is contingent upon the EoS and the rotational dynamics. This work proposes new universal relations regarding the star's surface, employing machine-learning techniques for regression. More specifically, we developed highly accurate universal relations for a neutron star's eccentricity, the star's ratio of the polar to the equatorial radius, and the effective gravitational acceleration at both the pole and the equator. Furthermore, we propose an accurate theoretical formula for $(d\log R(μ)/dθ)_{\max}$. This research addresses key astronomical aspects by utilizing these global parameters as features for the training phase of a neural network. Along the way, we introduce new effective parameterizations for each star's global surface characteristics. Our regression methodology enables accurate estimations of the star's surface $R(μ)$, its corresponding logarithmic derivative $d\log R(μ)/dθ$, and its effective acceleration due to gravity $g(μ)$ with accuracy better than $1 \%$. The analysis is performed for an extended sample of rotating configurations constructed using a large ensemble of 70 tabulated hadronic, hyperonic, and hybrid EoS models that obey the current multimessenger constraints and cover a wide range of stiffnesses. Above all, the suggested relations could provide an accurate framework for the star's surface estimation using data acquired from the NICER X-ray telescope or future missions, and constrain the EoS of nuclear matter when measurements of the relevant observables become available.

astro-ph.HE↗

arXiv2025

Counterfactual Explanations for k-means and Gaussian Clustering

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 work, we propose the use of counterfactuals to explain clustering solutions. First, we present a general definition for counterfactuals for model-based clustering that includes plausibility and feasibility constraints. Then we consider the counterfactual generation problem for k-means and Gaussian clustering assuming Euclidean distance. Our approach takes as input the factual, the target cluster, a binary mask indicating actionable or immutable features and a plausibility factor specifying how far from the cluster boundary the counterfactual should be placed. In the k-means clustering case, analytical mathematical formulas are presented for computing the optimal solution, while in the Gaussian clustering case (assuming full, diagonal, or spherical covariances) our method requires the numerical solution of a nonlinear equation with a single parameter only. We demonstrate the advantages of our approach through illustrative examples and quantitative experimental comparisons.

cs.LG↗

arXiv2024

Revisiting Silhouette Aggregation

Silhouette coefficient is an established internal clustering evaluation measure that produces a score per data point, assessing the quality of its clustering assignment. To assess the quality of the clustering of the whole dataset, the scores of all the points in the dataset are typically (micro) averaged into a single value. An alternative path, however, that is rarely employed, is to average first at the cluster level and then (macro) average across clusters. As we illustrate in this work with a synthetic example, the typical micro-averaging strategy is sensitive to cluster imbalance while the overlooked macro-averaging strategy is far more robust. By investigating macro-Silhouette further, we find that uniform sub-sampling, the only available strategy in existing libraries, harms the measure's robustness against imbalance. We address this issue by proposing a per-cluster sampling method. An experimental study on eight real-world datasets is then used to analyse both coefficients in two clustering tasks.

cs.LG↗

arXiv2024

Deep Clustering Using the Soft Silhouette Score: Towards Compact and Well-Separated Clusters

Unsupervised learning has gained prominence in the big data era, offering a means to extract valuable insights from unlabeled datasets. Deep clustering has emerged as an important unsupervised category, aiming to exploit the non-linear mapping capabilities of neural networks in order to enhance clustering performance. The majority of deep clustering literature focuses on minimizing the inner-cluster variability in some embedded space while keeping the learned representation consistent with the original high-dimensional dataset. In this work, we propose soft silhoutte, a probabilistic formulation of the silhouette coefficient. Soft silhouette rewards compact and distinctly separated clustering solutions like the conventional silhouette coefficient. When optimized within a deep clustering framework, soft silhouette guides the learned representations towards forming compact and well-separated clusters. In addition, we introduce an autoencoder-based deep learning architecture that is suitable for optimizing the soft silhouette objective function. The proposed deep clustering method has been tested and compared with several well-studied deep clustering methods on various benchmark datasets, yielding very satisfactory clustering results.

cs.LG↗

arXiv2023

UniForCE: The Unimodality Forest Method for Clustering and Estimation of the Number of Clusters

Estimating the number of clusters k while clustering the data is a challenging task. An incorrect cluster assumption indicates that the number of clusters k gets wrongly estimated. Consequently, the model fitting becomes less important. In this work, we focus on the concept of unimodality and propose a flexible cluster definition called locally unimodal cluster. A locally unimodal cluster extends for as long as unimodality is locally preserved across pairs of subclusters of the data. Then, we propose the UniForCE method for locally unimodal clustering. The method starts with an initial overclustering of the data and relies on the unimodality graph that connects subclusters forming unimodal pairs. Such pairs are identified using an appropriate statistical test. UniForCE identifies maximal locally unimodal clusters by computing a spanning forest in the unimodality graph. Experimental results on both real and synthetic datasets illustrate that the proposed methodology is particularly flexible and robust in discovering regular and highly complex cluster shapes. Most importantly, it automatically provides an adequate estimation of the number of clusters.

cs.LG↗

arXiv2023

Global $k$-means$++$: an effective relaxation of the global $k$-means clustering algorithm

The $k$-means algorithm is a prevalent clustering method due to its simplicity, effectiveness, and speed. However, its main disadvantage is its high sensitivity to the initial positions of the cluster centers. The global $k$-means is a deterministic algorithm proposed to tackle the random initialization problem of k-means but its well-known that requires high computational cost. It partitions the data to $K$ clusters by solving all $k$-means sub-problems incrementally for all $k=1,\ldots, K$. For each $k$ cluster problem, the method executes the $k$-means algorithm $N$ times, where $N$ is the number of datapoints. In this paper, we propose the \emph{global $k$-means\texttt{++}} clustering algorithm, which is an effective way of acquiring quality clustering solutions akin to those of global $k$-means with a reduced computational load. This is achieved by exploiting the center selection probability that is effectively used in the $k$-means\texttt{++} algorithm. The proposed method has been tested and compared in various benchmark datasets yielding very satisfactory results in terms of clustering quality and execution speed.

cs.LG↗