Nov 05, 2024 | We are very happy that our paper with PhD student Ioannis Sarridis and co-authors Christos Koutlis and Symeon Papadopoulos from CERTH/ITI has been published at the IEEE Transactions of Pattern Analysis and Machine Intelligence - I. Sarridis, C. Koutlis, S. Papadopoulos and C. Diou, “FLAC: Fairness-Aware Representation Learning by Suppressing Attribute-Class Associations” in IEEE Transactions on Pattern Analysis & Machine Intelligence, doi: 10.1109/TPAMI.2024.3487254.
- Paper: link
- Code: link
|
Oct 20, 2024 | Several things happened during the past six months, including a number of publications. We are also started beta testing Beam a platform to support behavior studies! |
Apr 10, 2024 | We are proud to announce Effector, a python package for global and regional feature effects, which is part of Vasilis Gkolemis’ work towards his PhD. For more information, check: |
Apr 01, 2024 | Our work (with Aristotelis Ballas) on Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization has been published at the IEEE Transactions on Artificial Intelligence! Article and preprint. |
Mar 28, 2024 | Congratulations to Ioannis Sarridis and all collaborators for making it to the top teams at the Face Recognition Challenge in the Era of Synthetic Data (FRCSyn)! As a result, we are happy to announce two publications: - P. Melzi et al., FRCSyn Challenge at WACV 2024: Face Recognition Challenge in the Era of Synthetic Data, WACV 2024
- P. Melzi et al., FRCSyn-onGoing: Benchmarking and comprehensive evaluation of real and synthetic data to improve face recognition systems, Information Fusion, 2024
|
Mar 19, 2024 | Thanks to the friends at the Stavanger University Hospital for inviting me to give the keynote speech on causal modeling for observational data analysis at the 2024 Annual meeting of the Norwegian National Network for Breast Cancer Research. |
Mar 05, 2024 | Last month I had the pleasure of |
Jan 10, 2024 | Our new project, MELIORA has just started! MELIORA is a collaboration between health scientists (including DND@HUA), ICT experts (including DIT@HUA), breast cancer patient representatives and other stakeholders to develop and evaluate “Multimodal Engagement and sustainable Lifestyle Interventions Optimizing breast cancer Risk reduction supported by Artificial intelligence”. |
Dec 11, 2023 | Today I had the opportunity to present our work on DALE, RHALE and RAM at the Department of Mathematics of the University of Patras. You can find the presentation slides here. |
Oct 08, 2023 | Vasileios Gkolemis presented our papers “Regionally Additive Models: Explainable-by-design models minimizing feature interactions” at the “Uncertainty Meets Explainability in Machine Learning” workshop at ECML-PKDD, and RHALE: Robust and Heterogeneity-aware Accumulated Local Effects at ECAI 2023. |
Sep 28, 2023 | The presentations from our “Uncertainty meets Explainability in Machine Learning” workshop are now available online. |
Aug 05, 2023 | We are happy to announce that our paper “Detection of Anomalies in Multivariate Time Series Using Ensemble Techniques” with A. Iliopoulos, J. Violos and I. Varlamis received the best paper award at the 2023 IEEE Big Data Service conference. |
Jul 04, 2023 | We will be hosting, along with Aristotelis Ballas, a tutorial session on Domain Generalization at this year’s IEEE Big Data Service conference. Edit: You can find the slides here |
Jun 21, 2023 | Today I gave an invited talk entitled “The promise and risks of Artificial Intelligence in healthcare: An introductory discussion”, at the Summer school: Health Communication & Health Inequalities Across the Health Professions in Greece & the U.S. |
May 10, 2023 | Vasileios Gkolemis and myself will be organizing the Uncertainty meets Explainability in Machine learning workshop in this year’s ECML-PKDD conference! Please check the CFP. |
Apr 18, 2023 | Our paper “Integrating nearest neighbors on neural network models for treatment effect estimation” with Niki Kiriakidou has been accepted for publication in the International Journal of Neural Systems! You may find a preprint in arxiv. |
Feb 28, 2023 | This semester I will be teaching a 6-week synchronous joint module with Rutgers University, along with my colleague, Matthew Matsagkanis! I am grateful to our students for their participation and for supporting this activity. |
Jan 30, 2023 | Today I gave an invited lecture to MSc students of Karolinska Institutet on digital health, big data analysis and AI in healthcare! |
Jan 03, 2023 | I will be giving a talk on Interpretable Machine Learning and the DALE method at the MeVer group at the Information Technologies Institute on Jan 04, 2023. Thanks to the colleagues at the MeVer group for the invitation! You may find the slides of the talk here |
Nov 01, 2022 | Our paper, DALE: Differential Accumulated Local Effects for efficient and accurate global explanations by V. Gkolemis, T. Dalamagas and myself has been accepted at ACML 2022! |
Sep 02, 2022 | New PhD position available on methods for quantifying and mitigating AI bias. Please check here for details (in Greek). |
Sep 01, 2022 | Please find pre-prints of our recent papers that will appear on SETN 2022 and IEEE Big Data Service and the Computing in Cardiology conference proceedings. - A. Ballas and C. Diou, “A Domain Generalization Approach for Out-Of-Distribution 12-lead ECG Classification with Convolutional Neural Networks”, IEEE Big Data Service 2022
- N. Kiriakidou and C. Diou, “An evaluation framework for comparing causal inference models”, SETN 2022
- A. Ballas and C. Diou, “Multi-layer Representation Learning for Robust OOD Image Classification”, SETN 2022
- A. Ballas, V. Papapanagiotou, A. Delopoulos and C. Diou, “Listen to your heart: A self-supervised approach for detecting murmur in heart-beat sounds for the Physionet 2022 challenge”, CinC 2022
|
Jul 15, 2022 | Our new project, RELEVIUM, will start on 1st of September. |
Jul 01, 2022 | We are happy to announce that our AIAI2022 paper with Niki Kiriakidou received the best paper award! Paper preprint is available on arxiv |