Differentially-private federated learning with long-term constraints using online mirror descent
Odeyomi, Olusola T.
Záruba, Gergely V.
MetadataShow full item record
Odeyomi, O., & Zaruba, G. (2021). Differentially-private federated learning with long-term constraints using online mirror descent. Paper presented at the IEEE International Symposium on Information Theory - Proceedings, , 2021-July 1308-1313. doi:10.1109/ISIT45174.2021.9518177
This paper discusses a fully decentralized online federated learning setting with long-term constraints. The fully decentralized setting removes communication and computational bottlenecks associated with a central server communicating with a large number of clients. Also, online learning is introduced to the federated learning setting to capture situations with time-varying data distribution. Practical federated learning settings are imposed with long-term constraints such as energy constraints, money cost constraints, time constraints etc. The clients are not obligated to satisfy any per round constraint, but they must satisfy these long-term constraints. To provide privacy to the shared local model updates of the clients, local differential privacy is introduced. An online mirror descent-based algorithm is proposed and its regret bound is obtained. The regret bound is compared with the regret bound of a differentially-private version of online gradient descent algorithm proposed for federated learning.
Click on the DOI link to access this conference paper at the publishers website (may not be free).