Artificial Intelligence and Learning Systems Laboratory

15/07/2024

Panagiotis Kouris, Γιώργος Αλεξανδρίδης and Andreas-Giorgos Stafylopatis work on text summarization based on semantic graphs has just been published open access by the Journal of Big Data by SpringerOpen!

Nowadays, due to the constantly growing amount of textual information, automatic text summarization constitutes an important research area in natural language processing. In this work, we present a novel framework that combines semantic graph representations along with deep learning predictions to g...

05/01/2024

Our joint work with Deeplab on Self-Supervised Learning for Visual Relationship Detection through Masked Bounding Box Reconstruction has just been presented at the Winter Conference on Applications of Computer Vision (WACV) 2024 as a poster!

29/12/2023

An article discussing data augmentation techniques for Reinforcement Learning agents in Game AI by PhD candidate Tasos Papagiannis, Dr. Γιώργος Αλεξανδρίδης (George Alexandridis) and Professor Andreas-Giorgos Stafylopatis has just been published on the Multi-Agent Systems special issue of the Applied Sciences MDPI Journal

Data augmentation is a promising technique in improving exploration and convergence speed in deep reinforcement learning methodologies. In this work, we propose a data augmentation framework based on generative models for creating completely novel states and increasing diversity. For this purpose, a...

05/07/2023

📝Want to use a counterfactual editor but don't know if its edits are truly minimal? Measuring inconsistency may help!
Our paper “Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editors”, delves deep into this.

🔍 We introduce a novel metric which uses iterative feedback steps to evaluate the inconsistency of editors!

🔍 The behavior and outputs of counterfactual editors varies a lot, but there is no universal ground truth for counterfactual edits. As such it is hard to tell what would be the optimal counterfactual.

🔍 We propose a using previous editor outputs as ground truth proxies.

🔍 We compare three editors on two datasets covering different types of use cases (adversarial and counterfactual, black and white box, with or without LLMs), gaining useful insights on the editors’ behavior.

🔍 Some insights : MiCE achieves lowest minimality but tends to leave remnant text spans, as indicated in the example below. This observation is also reflected in the inc@n: there is a higher value of inc@n when n is even indicating that it is easier to return to the original class.

📝 You can checkout the paper here: https://arxiv.org/abs/2305.17055 or talk to us in person at (come to our spotlight talk too).

w/ Eddie Dervakos, Orfeas Menis, Chryssa Zerva and George Stamou

06/02/2023

Professor Stefanos Kollias and Phd candidates Anastasis Arsenos and Paris Theofilou are among the organizing committee of the AI-enabled Medical Image Analysis Workshop and Covid-19 Diagnosis Competition (AI-MIA-COV19D) to be held in conjunction with IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) 2023 in Rhodes Island, Greece, 4 – 9 June, 2023. For more information (including submissions) please visit the following website

IEEE ICASSP 2023: AI-enabled Medical Image Analysis Workshop and Covid-19 Diagnosis Competition (AI-MIA-COV19D) The “AI-enabled Medical Image Analysis Workshop and Covid-19 Diagnosis Compet…

25/01/2023

The 1st day of the kick-off meeting is officially over 🎉 - Looking forward to a fruitful collaboration!



Υπουργείο Ψηφιακής Διακυβέρνησης Τμήμα Καινοτομίας & Βέλτιστων Πρακτικών ΥΠΕΣ Ελεύθερο Λογισμικό / Λογισμικό Ανοιχτού Κώδικα Εθνικό Κέντρο Τεκμηρίωσης ΕΔΥΤΕ - Εθνικό Δίκτυο Υποδομών Τεχνολογίας και Έρευνας - GRNET Πανεπιστήμιο Μακεδονίας University of Macedonia Πανεπιστήμιο Δυτικής Αττικής / University of West Attica Κοινωνία της Πληροφορίας International Hellenic University/Διεθνές Πανεπιστήμιο της Ελλάδος Athena Research Center Ιόνιο Πανεπιστήμιο - Ionian University Εθνικό Κέντρο Δημόσιας Διοίκησης και Αυτοδιοίκησης World Bank EU Science & Innovation Εθνικό Κέντρο Τεκμηρίωσης Digital EU European Parliament
CORDIS_EU The GovLab Council of the European Union ERC Research Consult European Commission

https://digigov.innohub.gr/about-us/

25/01/2023

O Κόμβος Καινοτομίας για την Ψηφιακή Διακυβέρνηση – GR digiGOV innoHUB υποστηρίζει την ανάπτυξη μιας νέας γενιάς δημόσιων υπηρεσιών που βασίζονται σε προηγμένες ψηφιακές ...

25/01/2023

The Innovation Hub for Digital Governance - – kicks off! 16 leading public bodies, academic and research institutions across Greece join forces to create and implement innovative digital solutions in the Public Administration utilizing advanced technologies such as , , , , and , with , and .



Υπουργείο Ψηφιακής Διακυβέρνησης Τμήμα Καινοτομίας & Βέλτιστων Πρακτικών ΥΠΕΣ ΕΔΥΤΕ - Εθνικό Δίκτυο Υποδομών Τεχνολογίας και Έρευνας - GRNET Πανεπιστήμιο Δυτικής Αττικής / University of West Attica Κοινωνία της Πληροφορίας International Hellenic University/Διεθνές Πανεπιστήμιο της Ελλάδος Πανεπιστήμιο Μακεδονίας University of Macedonia Athena Research Center Ιόνιο Πανεπιστήμιο - Ionian University Εθνικό Κέντρο Δημόσιας Διοίκησης και Αυτοδιοίκησης Ελεύθερο Λογισμικό / Λογισμικό Ανοιχτού Κώδικα World Bank EU Science & Innovation Εθνικό Κέντρο Τεκμηρίωσης Digital EU European Commission European Parliament
CORDIS_EU The GovLabCouncil of the European Union ERC Research Consult

19/01/2023

Lab members’ George Ioannou, Γιώργος Αλεξανδρίδης and Andreas-Giorgos Stafylopatis work on Online Batch Selection for Enhanced Generalization in Imbalanced Datasets has just been published on the Deep Neural Networks and Optimization Algorithms special issue of the Algorithms MDPI journal

Importance sampling, a variant of online sampling, is often used in neural network training to improve the learning process, and, in particular, the convergence speed of the model. We study, here, the performance of a set of batch selection algorithms, namely, online sampling algorithms that process...

05/01/2023

Ο Τομέας Τεχνολογίας Πληροφορικής και Υπολογιστών της Σχολής Ηλεκτρολόγων Μηχανικών και Μηχανικών Υπολογιστών του Εθνικού Μετσόβιου Πολυτεχνείου, και το Διατμηματικό Πρόγραμμα Μεταπτυχιακών Σπουδών «Επιστήμη Δεδομένων και Μηχανική Μάθηση» σας προσκαλούν σε επιστημονική ημερίδα με θέμα τις σύγχρονες ερευνητικές προκλήσεις στην Επιστήμη Υπολογιστών. Η ημερίδα θα γίνει την Δευτέρα 9 Ιανουαρίου 2023, στην Αίθουσα Τελετών, στο ισόγειο του Κτηρίου Διοίκησης, στην Πολυτεχνειούπολη Ζωγράφου, σύμφωνα με το παρακάτω πρόγραμμα.

Vassilis Zikas, Vasiliki (Vasia) Kalavri, Constantine Caramanis, Manolis Zampetakis

25/11/2022

Friday 25/1114:00-15:00: High Performance computing, Artificial Intelligence and research infrastructures: The driving force for digital transformation in Gr...