Aristotelis Ballas

ballas_s.jpg

Lab 5.7

Omirou 9, Tavros, 17778

Athens, Greece

Welcome to my personal wannabe website. I am Aristotelis, an aspiring PhD student researching Algorithms for Robust Representation Learning at the Harokopio University of Athens, under the supervision of Prof. Christos Diou. I also hold a diploma in Electrical and Computer Engineering from the National Tecnical University of Athens.

Currently, I’m interested in reasearching out-of-distribution robustness, domain generalization and AI in healthcare. In addition to working towards my PhD, I’m also involved in some other things, which you can hopefully find throughout the website.

news

Mar 4, 2025 Thrilled to announce, that our paper with Christos Diou, “Gradient-Guided Annealing for Domain Generalization”, has been accepted in CVRP2025! In our research, we tackle the problem of Domain Generalization (DG) from a gradient perspective, observing that conflicting gradients in datasets with diverse samples cause models to converge to suboptimal parameter configurations.The proposed Gradient-Guided Annealing (GGA) algorithm identifies loss surface minima that exhibit improved robustness by iteratively annealing its parameters, searching for points where gradients align across domains. You can learn more in the early access paper on ArXiv. Code available on GitHub.
Dec 10, 2024 Our research paper named “On the Out-Of-Distribution Robustness of Self-Supervised Representation Learning for Phonocardiogram Signals” got accepted in IEEE Access. You can check out the preprint manuscript on ArXiv and the open-source codebase on GitHub.
Sep 11, 2024 Recently presented our short-paper “CycleMix: Mixing Source Domains for Domain Generalization in Style-Dependent Data” in SETN 2024. Feel free to take a look at the preprint and code.
Mar 18, 2024 Our paper “Multi-Scale and Multi-Layer Contrastive Learning for Domain Generalization”, got accepted and is now published at the IEEE Transactions on Artificial Intelligence journal. Feel free to check out the paper and code.
Dec 4, 2023 We recently submitted our latest research paper named “On the Out-Of-Distribution Robustness of Self-Supervised Representation Learning for Phonocardiogram Signals” for review. You can take a look at the preprint manuscript on ArXiv and the open-source codebase on GitHub.