Gergely D. Németh

PhD Student

Gergely Dániel Németh was an ELLIS PhD student between 2021 and 2025.

He studied computer science at the Budapest University of Technology and Economics and at the University of Manchester, where he worked on Natural Language Processing (NLP). Later, he worked on applied Machine Learning (ML) projects focused on Computer Vision (CV) at Asura Technologies, a Hungarian StartUp leading in smart traffic applications. He started his PhD at ELLIS Alicante in November 2021. His PhD topics was Federated Learning (FL). His work focused on the model, participation and data heterogeneity in FL as well as privacy and fairness in FL. His supervisors are Nuria Oliver (ELLIS Alicante), Miguel Angel Lozano (University of Alicante) and Novi Quadrianto (University of Sussex).

Website: https://negedng.github.io/

Link to ORCID profile:

https://orcid.org/0000-0002-9737-6519

Publications in association with ELLIS Alicante

2025

10/14
Dubrovnik, HR

Németh, G. D., Fanì, E., Ng, Y. J., Caputo, B., Lozano, M. A., Oliver, N., & Quadrianto, N. (2025). FedDiverse: Tackling Data Heterogeneity in Federated Learning with Diversity-Driven Client Selection. 3rd IEEE International Conference on Federated Learning Technologies and Applications (FLTA25).

09/12
Alicante, ES

Németh, G. D. (2025). Relaxing Core Assumptions: the Impact of Data, Model and Participation Heterogeneity on Performance, Privacy and Fairness in Federated Learning. PhD Thesis, University of Alicante.

Oral

02/27

Németh, G. D., Lozano, M. A., Quadrianto, N., & Oliver, N. (2025). Privacy and Accuracy Implications of Model Complexity and Integration in Heterogeneous Federated Learning. IEEE Access, 13, 40258-40274.

2023

11/29

Németh, G. D., Lozano, M. A., Quadrianto, N., & Oliver, N. (2023). Addressing Membership Inference Attack in Federated Learning with Model Compression. arXiv preprint:2311.17750.

2022

12/21

Németh, G. D., Lozano, M. A., Quadrianto, N., & Oliver, N. (2022). A Snapshot of the Frontiers of Client Selection in Federated Learning. Transactions on Machine Learning Research.