Bardh Prenkaj
Bardh Prenkaj
Home
Experience
Honors & Awards
Projects
Talks
Courses
Publications
Contact
Light
Dark
Automatic
deep learning
RAZOR: Sharpening Knowledge by Cutting Bias with Unsupervised Text Rewriting
Despite the widespread use of LLMs due to their superior performance in various tasks, their high computational costs often lead …
Shuo Yang
,
Bardh Prenkaj
,
Gjergji Kasneci
PDF
Cite
Code
DOI
Unifying Evolution, Explanation, and Discernment, A Generative Approach for Dynamic Graph Counterfactuals
I gave a talk on my paper on Dynamic Graph Counterfactuality accepted as oral presentation at KDD'24.
Oct 17, 2024 5:00 PM — 6:00 PM
Online
Bardh Prenkaj
PDF
Code
Slides
Video
Unifying Evolution, Explanation, and Discernment: A Generative Approach for Dynamic Graph Counterfactuals
We present GRACIE (Graph Recalibration and Adaptive Counterfactual Inspection and Explanation), a novel approach for generative …
Bardh Prenkaj
,
Mario Villaizan-Vallelado
,
Tobias Leemann
,
Gjergji Kasneci
PDF
Cite
Code
Poster
Slides
DOI
Robust Stochastic Graph Generator for Counterfactual Explanations
I gave a talk on my paper on Generative Graph Counterfactuality accepted as oral presentation at AAAI'24.
Jun 15, 2024 5:00 PM — 6:00 PM
Online
Bardh Prenkaj
PDF
Code
Slides
Digging into the Landscape of Graphs Counterfactual Explainability
The lab provides a hands-on experience for users to develop and evaluate Graph Counterfactual Explanation methods using the GRETEL framework, covering challenges, building pipelines, customizing solutions, and analyzing performance in diverse datasets.
Feb 21, 2024 2:00 PM — 3:45 PM
Vancouver, Canada
Mario Alfonso Prado-Romero
,
Bardh Prenkaj
,
Giovanni Stilo
Code
Graphs Counterfactual Explainability A Comprehensive Landscape
The tutorial covers generating counterfactual explanations for Graph Neural Networks, addressing theoretical foundations, challenges, definitions, methods, and benchmarking for improved interpretability.
Feb 21, 2024 10:45 AM — 12:30 PM
Vancouver, Canada
Mario Alfonso Prado-Romero
,
Bardh Prenkaj
,
Giovanni Stilo
PDF
Code
Hands-on, Building Convolutional Neural Networks and Optimizing them to Recognize Handwritten Digits
May 25, 2023 3:00 PM — May 23, 2023 5:10 PM
L'Aquila, Italy
Bardh Prenkaj
Plotly.plus, an Improved Dataset for Visualization Recommendation
In this short paper, we explored the challenges and solutions of considering a specific plot as (non)significative from a perceptual point-of-view.
Oct 16, 2022 6:00 PM — 6:10 PM
Online
Luca Podo
,
Paola Velardi
PDF
Slides
Video
Explaining Anomalies in Patient Daily Behaviour Profiles
In this presentation, I presented future directions of explainable anomaly detection in daily routine behaviours of older patients.
Jul 12, 2022 9:00 AM — 9:20 AM
Online
Bardh Prenkaj
Project
Slides
Hidden space deep sequential risk prediction on student trajectories
Online learning environments (OLEs) have seen a continuous increase over the past decade and a sudden surge in the last year, due to …
Bardh Prenkaj
,
Damiano Distante
,
Stefano Faralli
,
Paola Velardi
Cite
DOI
»
Cite
×