12 citations
4 papers
Stream Learning: Partition-Fair Gossip Learning Without Tokens
Fabien Mathieu, Alexandre Pham, Maria Gradinariu Potop-Butucaru +1
In gossip learning, a network of nodes trains a shared model collaboratively, without a central coordinator, by repeatedly exchanging parts of their local models. The state-of-the-…
LIFT: Byzantine Resilient Hub-Sampling
Mohamed Amine Legheraba, Nour Rachdi, Maria Gradinariu Potop-Butucaru +1
Recently, a novel peer sampling protocol, Elevator, was introduced to construct network topologies tailored for emerging decentralized applications such as federated learning and b…
Data Poisoning Attacks in Gossip Learning
Alexandre Pham, Maria Potop-Butucaru, Sébastien Tixeuil +1
Traditional machine learning systems were designed in a centralized manner. In such designs, the central entity maintains both the machine learning model and the data used to adjus…
No more glowing in the dark: How deep learning improves exposure date estimation in thermoluminescence dosimetry
Florian Mentzel, Evelin Derugin, Hannah Jansen +4
The time- or temperature-resolved detector signal from a thermoluminescence dosimeter can reveal additional information about circumstances of an exposure to ionizing irradiation.…