OZGU GOKSU
2718886G@student.gla.systa-s.com
Research title: Beyond Labels and Centralisation: Representation Learning Through Data Curation
Necessary cookies enable core functionality. The website cannot function properly without these cookies, and can only be disabled by changing your browser preferences.
Analytical cookies help us improve our website. We use Google Analytics. All data is anonymised.
Clarity helps us to understand our users’ behaviour by visually representing their clicks, taps and scrolling. All data is anonymised.
2718886G@student.gla.systa-s.com
Research title: Beyond Labels and Centralisation: Representation Learning Through Data Curation
Göksu, Özgü and Pugeault, Nicolas ORCID: https://orcid.org/0000-0002-3455-6280
(2026)
FedQuad: Federated Stochastic Quadruplet Learning to Mitigate Data Heterogeneity.
In: 3rd IEEE International Conference on Federated Learning Technologies and Applications (FLTA25), Dubrovnik, Croatia, 14-17 October 2025,
pp. 262-269.
ISBN 9798331556709
(doi: 10.1109/FLTA67013.2025.11336470)
Goksu, Ozgu and Pugeault, Nicolas ORCID: https://orcid.org/0000-0002-3455-6280
(2026)
Hybrid-Regularized Magnitude Pruning for Robust Federated Learning under Covariate Shift.
In: International Symposium on Edge intelligence, Trustworthy and Decentralized Artificial Intelligence (iEDGE 2025), Dubrovnik, Croatia, 14-17 October 2025,
pp. 588-592.
ISBN 9798331556709
(doi: 10.1109/FLTA67013.2025.11336795)
Goksu, Ozgu and Pugeault, Nicolas ORCID: https://orcid.org/0000-0002-3455-6280
(2024)
The Bad Batches: Enhancing Self-Supervised Learning in Image Classification Through Representative Batch Curation.
In: IEEE World Congress on Computational Intelligence (IEEE WCCI 2024), Yokohama, Japan, 30 Jun - 05 Jul 2024,
pp. 1-8.
ISBN 9798350359312
(doi: 10.1109/IJCNN60899.2024.10650183)
Göksu, Özgü and Pugeault, Nicolas ORCID: https://orcid.org/0000-0002-3455-6280
(2026)
FedQuad: Federated Stochastic Quadruplet Learning to Mitigate Data Heterogeneity.
In: 3rd IEEE International Conference on Federated Learning Technologies and Applications (FLTA25), Dubrovnik, Croatia, 14-17 October 2025,
pp. 262-269.
ISBN 9798331556709
(doi: 10.1109/FLTA67013.2025.11336470)
Goksu, Ozgu and Pugeault, Nicolas ORCID: https://orcid.org/0000-0002-3455-6280
(2026)
Hybrid-Regularized Magnitude Pruning for Robust Federated Learning under Covariate Shift.
In: International Symposium on Edge intelligence, Trustworthy and Decentralized Artificial Intelligence (iEDGE 2025), Dubrovnik, Croatia, 14-17 October 2025,
pp. 588-592.
ISBN 9798331556709
(doi: 10.1109/FLTA67013.2025.11336795)
Goksu, Ozgu and Pugeault, Nicolas ORCID: https://orcid.org/0000-0002-3455-6280
(2024)
The Bad Batches: Enhancing Self-Supervised Learning in Image Classification Through Representative Batch Curation.
In: IEEE World Congress on Computational Intelligence (IEEE WCCI 2024), Yokohama, Japan, 30 Jun - 05 Jul 2024,
pp. 1-8.
ISBN 9798350359312
(doi: 10.1109/IJCNN60899.2024.10650183)