Publications

Co-Recursive Semantic Self-Extension: A Mathematical Foundation for Open-Ended Intelligence

Simon Hegelich, Bardh Prenkaj, Habiba Sarhan, Morteza Shahrezaye, Kolja Hegelich, Erik Cambria, Christiane Montag

Causal Routing for Unlearning

Bardh Prenkaj, Andrea D'Angelo, Davide Mottin, Federico Fontana, Davide Gabrielli, Paola Velardi, Stefano Faralli

High-Dimensional Online Change Point Detection with Adaptive Thresholding and Interpretability

Sven Jacob, Bardh Prenkaj, Weijia Shao, Gjergji Kasneci

Beyond Binary Rewards: A Comparative Study of Reward Design for Reinforcement Unlearning

Efstratios Zaradoukas, Davide Gabrielli, Bardh Prenkaj, Gjergji Kasneci

Active Tabular Augmentation via Policy-Guided Diffusion Inpainting

Zheyu Zhang, Shuo Yang, Bardh Prenkaj, Gjergji Kasneci

SAGE: Sparse Adaptive Guidance for Dependency-Aware Tabular Data Generation

Shuo Yang, Zheyu Zhang, Bardh Prenkaj, Gjergji Kasneci

TabSCM: A practical Framework for Generating Realistic Tabular Data

Sven Jacob, Bardh Prenkaj, Weijia Shao, Gjergji Kasneci

Reinforcement Unlearning via Group Relative Policy Optimization

Efstratios Zaradoukas, Bardh Prenkaj, Gjergji Kasneci

Analysing the Safety Pitfalls of Steering Vectors

Yuxiao Li, Alina Fastowski, Efstratios Zaradoukas, Bardh Prenkaj, Gjergji Kasneci

Beyond Edge Deletion: A Comprehensive Approach to Counterfactual Explanation in Graph Neural Networks

Matteo De Sanctis, Riccardo De Sanctis, Stefano Faralli, Paola Velardi, Bardh Prenkaj

A Multi-Agent Framework for Interpreting Multivariate Physiological Time Series

Davide Gabrielli, Paola Velardi, Stefano Faralli, Bardh Prenkaj

Moral Lenses, Political Coordinates: Towards Ideological Positioning of Morally Conditioned LLMs

Chenchen Yuan, Bolei Ma, Zheyu Zhang, Bardh Prenkaj, Frauke Kreuter, Gjergji Kasneci

COunterfactual Reasoning for Temporal EXplanations: Plausible and Robust Explanations for EEG-Based Seizure Detection

Martina Zannotti, Bardh Prenkaj, Marco Piangerelli, Flavio Corradini, Gjergji Kasneci

Seamless monitoring of stress levels leveraging a foundational model for time sequences

Davide Gabrielli, Bardh Prenkaj, Paola Velardi

AI on the Pulse: Real-Time Health Anomaly Detection with Wearable and Ambient Intelligence

Davide Gabrielli, Bardh Prenkaj, Paola Velardi, Stefano Faralli

Injecting Falsehoods: Adversarial Man-in-the-Middle Attacks Undermining Factual Recall in LLMs

Alina Fastowski, Bardh Prenkaj, Yuxiao Li, Gjergji Kasneci

From Confidence to Collapse in LLM Factual Robustness

Alina Fastowski, Bardh Prenkaj, Gjergji Kasneci

Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs

Shuo Yang, Zheyu Zhang, Bardh Prenkaj, Gjergji Kasneci

CURE: Controlled Unlearning for Robust Embeddings - Mitigating Conceptual Shortcuts in Pre-Trained Language Models

Aysenur Kocak, Shuo Yang, Bardh Prenkaj, Gjergji Kasneci

TRADES: Generating Realistic Market Simulations with Diffusion Models

Leonardo Berti, Bardh Prenkaj, Paola Velardi

Exploring Ensemble Strategies for Graph Counterfactual Explanations

Mario Alfonso Prado-Romero, Bardh Prenkaj, Giovanni Stilo

Probabilistic Aggregation and Targeted Embedding Optimization for Collective Moral Reasoning in Large Language Models

Chenchen Yuan, Zheyu Zhang, Shuo Yang, Bardh Prenkaj, Gjergji Kasneci

Not All Features Deserve Attention: Graph-Guided Dependency Learning for Tabular Data Generation with Language Models

Zheyu Zhang, Shuo Yang, Bardh Prenkaj, Gjergji Kasneci

SCISSOR: Mitigating Semantic Bias through Cluster-Aware Siamese Networks for Robust Classification

Shuo Yang, Bardh Prenkaj, Gjergji Kasneci

Graph Inverse Style Transfer for Counterfactual Explainability

Bardh Prenkaj, Efstratios Zaradoukas, Gjergji Kasneci

Position: Efficient General Intelligence requires Neuro-Symbolic Integration: Pillars, Benchmarks, and Beyond

Felix Steinbauer, Bardh Prenkaj, Efstratios Zaradoukas, Mrigyen Sawant, Florian Kofler, Gjergji Kasneci

RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text Rewriting

Shuo Yang, Bardh Prenkaj, Gjergji Kasneci

Semantically Guided Representation Learning For Action Anticipation

Anxhelo Diko, Danilo Avola, Bardh Prenkaj, Federico Fontana, Luigi Cinque

GRETEL 2.0: Generation and Evaluation of Graph Counterfactual Explanations Evolved

Mario Alfonso Prado-Romero, Bardh Prenkaj, Giovanni Stilo

Unifying Evolution, Explanation, and Discernment: A Generative Approach for Dynamic Graph Counterfactuals

Bardh Prenkaj, Mario Villaizan-Vallelado, Tobias Leemann, Gjergji Kasneci

Is My Data Safe? Predicting Instance-Level Membership Inference Success for White-box and Black-box Attacks

Tobias Leemann, Bardh Prenkaj, Gjergji Kasneci

Towards Non-Adversarial Algorithmic Recourse

Tobias Leemann, Martin Pawelczyk, Bardh Prenkaj, Gjergji Kasneci

Agnostic Visual Recommendation Systems: Open Challenges and Future Directions

Luca Podo, Bardh Prenkaj, Paola Velardi

Robust Stochastic Graph Generator for Counterfactual Explanations

Mario Alfonso Prado-Romero, Bardh Prenkaj, Giovanni Stilo

Unsupervised Detection of Behavioural Drifts With Dynamic Clustering and Trajectory Analysis

Bardh Prenkaj, Paola Velardi

Are Generative-Based Graph Counterfactual Explainers Worth It?

Mario Alfonso Prado-Romero, Bardh Prenkaj, Giovanni Stilo

Multimodal Motion Conditioned Diffusion Model for Skeleton-based Video Anomaly Detection

Alessandro Flaborea, Luca Collorone, Guido D'Amely, Stefano D'Arrigo, Bardh Prenkaj, Fabio Galasso

Adapting to Change: Robust Counterfactual Explanations in Dynamic Data Landscapes

Bardh Prenkaj, Mario Villaizan-Vallelado, Tobias Leemann, Gjergji Kasneci

A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges

Mario Alfonso Prado-Romero, Bardh Prenkaj, Giovanni Stilo, Fosca Giannotti

Are we certain it is anomalous?

Alessandro Flaborea, Bardh Prenkaj, Bharti Munjal, Marco Aurelio Sterpa, Dario Aragona, Luca Podo, Fabio Galasso

Revisiting CounteRGAN for Counterfactual Explainability of Graphs

Mario Alfonso Prado-Romero, Bardh Prenkaj, Giovanni Stilo

Developing and Evaluating Graph Counterfactual Explanation with GRETEL

Mario Alfonso Prado-Romero, Bardh Prenkaj, Giovanni Stilo

Ensemble approaches for Graph Counterfactual Explanations

Mario Alfonso Prado-Romero, Bardh Prenkaj, Giovanni Stilo, Alessandro Celi, Ernesto Estevanell-Valladares, Daniel Alejandro Valdés-Pérez

A self-supervised algorithm to detect signs of social isolation in the elderly from daily activity sequences

Bardh Prenkaj, Dario Aragona, Alessandro Flaborea, Fabio Galasso, Saverio Gravina, Luca Podo, Emilia Reda, Paola Velardi

Hidden space deep sequential risk prediction on student trajectories

Bardh Prenkaj, Damiano Distante, Stefano Faralli, Paola Velardi

Latent and sequential prediction of the novel coronavirus epidemiological spread

Dario Aragona, Luca Podo, Bardh Prenkaj, Paola Velardi

Unsupervised boosting-based autoencoder ensembles for outlier detection

Hamed Sarvari, Carlotta Domeniconi, Bardh Prenkaj, Giovanni Stilo

CoRoNNa: a deep sequential framework to predict epidemic spread

Dario Aragona, Luca Podo, Bardh Prenkaj, Paola Velardi

Challenges and solutions to the student dropout prediction problem in online courses

Bardh Prenkaj, Giovanni Stilo, Lorenzo Madeddu

A reproducibility study of deep and surface machine learning methods for human-related trajectory prediction

Bardh Prenkaj, Paola Velardi, Damiano Distante, Stefano Faralli

A survey of machine learning approaches for student dropout prediction in online courses

Bardh Prenkaj, Paola Velardi, Giovanni Stilo, Damiano Distante, Stefano Faralli

MIMOSE: multimodal interaction for music orchestration sheet editors

Andrea Coletta, Maria De Marsico, Bardh Prenkaj, Domenicomichele Silvestri

House in the (biometric) cloud: a possible application

Maria De Marsico, Eugenio Nemmi, Bardh Prenkaj, Gabriele Saturni

A smart peephole on the cloud

Maria De Marsico, Eugenio Nemmi, Bardh Prenkaj, Gabriele Saturni