Lydia Y. Chen is a Professor in the Department of Computer Science at the University of Neuchatel in Switzerland and Delft University of Technology in the Netherlands. Prior to joining TU Delft, she was a research staff member at the IBM Research Zurich Lab from 2007 to 2018. She holds a PhD from Pennsylvania State University and a BA from National Taiwan University. Her research interests are distributed machine learning systems, generative AI, and dependability and privacy enhancing technologies. More specifically, her work focuses on developing machine learning and stochastic models, and applying these techniques to application domains, such as data centers, edge systems, semi-conductor and material science.

• DepMat Project (2023-27) from Dutch National Science Fondation, Perspectief programme
• Dapprox Project (2017-2021) from Swiss National Science Fondation NRP 75 programme
• Women in Big DataProject (2018-2022) from Swiss National Science Fondation NRP 75 programme
• GENiC project (2013-2015) from EU FP6 programme
• LoadOpt project (2011 -2015) from Swiss National Science Foundation regular programme

• Distributed machine learning systems,
• Modeling and scaling of generative AI systems
• Advanced statistics
• Simulation and queueing systems

Huang, J., Zhao, Z., Chen, L.Y. & Roos, S. (2023) Fabricated Flips: Poisoning Federated Learning without Data IEEE/IFIP International Conference on Dependable Systems and Network, pages 274–287

Zhu, C, Roos, S.& Chen, L.Y. (2023) LeadFL: Client Self-Defense against Model Poisoning in Federated Learning, ICML, Proceedings of Machine Learning Research, pages 43158–43180

Luopan, Y., Han, R., Zhang, Q., Liu, C., Wang, G. & Chen, L.Y. (2023) “FedKNOW: Federated Continual Learning with Signature Task Knowledge Integration at Edge.” In Proceedings of IEEE International Con- ference on Data Engineering (ICDE),  pages 341–354

Ghiassi, A., Birke, R. and Chen, L.Y. (2023) “Robust Learning via Golden Symmetric Loss of (un)Trusted Labels.” In Proceedings of SIAM International Conference on Data Mining (SDM), pages 568–576

Zhao, Z. Cerf, S., Birke, R., Robu, B., Bouchenak, S., Mokhtar, S. & Chen, L.Y. (2021) “Enhancing Ro- bustness of On-Line Learning Models on Highly Noisy Data.” IEEE Tran,sactions on Dependable Secure Computing, Vol. 18, No. 9, pages 2177-2192

Hong, C., Ghiassi, A., Zhou, Y., Birke, R. & Chen, L.Y. (2021) “Online Label Aggregation: A Variational Bayesian Approach.” In Proceedings of ACM Web Conference (WWW), pages 97-112

Cox, B., Galjaard, J., Ghiassi, A., Birke, R. & Chen, L.Y. (2021) “MASA: Responsive Multi-DNN Infer- ence on the Edge.” In Proceedings of IEEE Conference on Pervasive Computing and Communications (PerCom), pages 1-10

Birke, R., Perez, J., Qiu, Z., Björkqvist, M. & Chen, L.Y. (2017) “Power of Redundancy: Designing Partial Replication for Multi-tier Applications.” In Proceedings of IEEE International Conference on Computer Communications (INFOCOM), pages 1-9

Birke, R., Giurgiu, I., Chen, L.Y., Wiesmann, D. & Engbersen, T. (2014) “Failures Analysis of Virtual and Physical Machines: Patterns, Causes and Characteristics.” In proceedings of IEEE/IFIP International Conference on Dependable Systems and Networks (DSN), pages 1-12

• Toutes les publications : Distributed Learning Systems Lab TU Delft