Simula UiB and Inria collaborate on private distributed learning
Published:
A new Associate Team with Inria at Simula UiB will bring together researchers from Norway, France, and Taiwan to collaborate on Private Real-time Distributed Learning (PRiDeL).
Simula UiB is pleased to announce the new collaboration with the MARACAS team at Inria Lyon, and the Coding and Information Theory Group at the National Yang Ming Chiao Tung University (NYCU) in Taiwan.
The project, PRiDeL (Private Real-time Distributed Learning), focuses on the co-design of distributed learning algorithms and communication strategies that incorporate privacy guarantees for real-time and streaming data.
Sensors and connected devices increasingly process data locally, making distributed learning techniques such as federated learning (FL) both possible and practical.
FL enables raw data to remain on-device. It can be viewed as a form of compression, reducing communication overhead, energy consumption and latency. It can also improve data privacy, as raw data is not communicated directly.
However, the model updates communicated between devices can still leak sensitive information. PRiDeL addresses this challenge by developing learning algorithms with built-in privacy guarantees.
The associate team will be jointly led by Principal Investigator Hsuan-Yin Lin from the Department of Information Theory at Simula UiB, and Principal Investigator Malcolm Egan from the MARACAS team at Inria Lyon, with Yu-Chih (Jerry) Huang at NYCU serving as Co-PI.
The collaboration brings together complementary expertise in information theory, statistical signal processing, secure and reliable communication, and computing networks. The project runs from 2026 to 2028.
About Inria associate teams
Inria is France's national research institute for digital science and technology. The Inria Associate Team programme supports renewable joint research projects, running three years at a time, between an Inria project team and a research team from abroad. The two partners jointly define a scientific ambition, a research plan, and a bilateral exchange programme.
PRiDeL is the sixth associate team established between Inria and Simula since 2021. It is part of a long-standing collaboration, which was further strengthened when Simula and Inria signed a new framework agreement for scientific cooperation on 10 February 2026. The framework sets out a joint strategic research and innovation agenda spanning areas of shared interest, particularly including artificial intelligence, cryptography and cybersecurity, high-performance computing, and quantum technology.