Yongli Mou

Yongli Mou

Ph.D. student in Computer Science at RWTH Aachen University, Germany

Posts by Collection

news

Best Technical Implementation Award and First Price of Industry Challenge at Blockchain Hackathon 2021 Germany

Published:

AISpace team, including Yongli Mou (as team leader), Jiahui Geng, Xiaoli Yang, Shijie Nie, Chunmiao Li, Yongzhao Li and Lucas Regh, won the best technical implementation award and won the industry challenge at the Blockchain Hackathon 2021. we presented the idea to combine blockchain, federated learning and privacy enhancing technologies to overcome the data privacy challenges in AI, to build an AI digital asset marketplace, to connect data owners, data users, algorithm developers, algorithm users and computing providers, to encourage the corporation between AI service participants, and to establish the decentralized, autonomous and trustworthy AI infrastructure network.

portfolio

projects

publications

Optimized Federated Learning on Class-Biased Distributed Data Sources

Published in In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 2021

Download paper here

Recommended citation: Mou Y, Geng J, Welten S, Chun R, Decker S, Beyan O. (2021). "Optimized Federated Learning on Class-biased Distributed Data Sources." In Joint European Conference on Machine Learning and Knowledge Discovery in Databases. ECML PKDD 2021. Communications in Computer and Information Science, vol 1524. Springer, Cham. https://doi.org/10.1007/978-3-030-93736-2_13

Blockchain-based Cross-organizational Workflow Platform

Published in 2022 IEEE International Conference on Cloud Computing Technology and Science, 2022

Download paper here

Recommended citation: Geng J, Rehman AA, Mou Y, Decker S, Rong C. "Blockchain-based Cross-organizational Workflow Platform" In2022 IEEE International Conference on Cloud Computing Technology and Science (CloudCom). 2022 Dec 13 (pp. 53-59)

pFedV: Mitigating Feature Distribution Skewness via Personalized Federated Learning with Variational Distribution Constraints

Published in In 27th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2023, 2023

Download paper here

Recommended citation: Mou, Y., Geng, J., Zhou, F., Beyan, O., Rong, C. and Decker, S. (2023). "pFedV: Mitigating Feature Distribution Skewness via Personalized Federated Learning with Variational Distribution Constraints." In Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2023. (pp. 283-294). Springer Nature, Cham.

talks

teaching