Publication
Federated learning with uncertainty-based client clustering for fleet-wide fault diagnosis
Related publications (36)
ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference
Nikita Durasov, Minh Hieu Lê, Nik Joel Dorndorf
Whereas the ability of deep networks to produce useful predictions on many kinds of data has been amply demonstrated, estimating the reliability of these predictions remains challenging. Sampling approaches such as MC-Dropout and Deep Ensembles have emerge ...
2024Design of an Open-Loop Pile-Oscillation Program in the CROCUS Reactor
Andreas Pautz, Vincent Pierre Lamirand, Thomas Jean-François Ligonnet, Axel Guy Marie Laureau
As a follow-up to the CEA-EPFL PETALE experimental program on stainless steel nuclear data, the EPFL initiated an open-loop pile-oscillation experimental program in the CROCUS reactor: BLOOM. A reproduction of the critical experiments of PETALE, the progra ...
2024The Societal and Scientific Importance of Inclusivity, Diversity, and Equity in Machine Learning for Chemistry
While the introduction of practical deep learning has driven progress across scientific fields, recent research highlighted that the requirement of deep learning for ever-increasing computational resources and data has potential negative impacts on the sci ...
2023Personalized Privacy-Preserving Distributed Learning on Heterogeneous Data
Michael Christoph Gastpar, Aditya Pradeep
One major challenge in distributed learning is to efficiently learn for each client when the data across clients is heterogeneous or non iid (not independent or identically distributed). This provides a significant challenge as the data of the other client ...
2023Uncertainty quantification in machine learning for engineering design and health prognostics: A tutorial
On top of machine learning (ML) models, uncertainty quantification (UQ) functions as an essential layer of safety assurance that could lead to more principled decision making by enabling sound risk assessment and management. The safety and reliability impr ...
2023Data-driven IQC-Based Robust Control Design for Hybrid Micro-disturbance Isolation Platform
Alireza Karimi, Vaibhav Gupta, Elias Sebastian Klauser
A novel approach for robust controller synthesis, which models uncertainty as an elliptical set, is proposed in the paper. Given a set of frequency response functions of linear time-invariant (LTI) multiple-input multiple-output (MIMO) systems, the approac ...
2023Environment rather than breed or body site shapes the skin bacterial community of healthy sheep as revealed by metabarcoding
Christof Holliger, Alexander Mathis, Emmanuelle Rohrbach, Laetitia Janine Andrée Cardona
Background: The skin is inhabited by a variety of micro-organisms, with bacteria representing the predominant taxon of the skin microbiome. In sheep, the skin bacterial community of healthy animals has been addressed in few studies, only with culture-based ...
2023Generating Higher-Fidelity Synthetic Datasets with Privacy Guarantees
Boi Faltings, Aleksei Triastcyn
We consider the problem of enhancing user privacy in common data analysis and machine learning development tasks, such as data annotation and inspection, by substituting the real data with samples from a generative adversarial network. We propose employing ...
MDPI2022Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data
Martin Jaggi, Sebastian Urban Stich, Tao Lin, Sai Praneeth Reddy Karimireddy
Decentralized training of deep learning models is a key element for enabling data privacy and on-device learning over networks. In realistic learning scenarios, the presence of heterogeneity across different clients' local datasets poses an optimization ch ...
JMLR-JOURNAL MACHINE LEARNING RESEARCH2021Modelling the Intracellular Environment under Uncertainty, from Post-translational Modification to Metabolic Networks
Robin Alexander Denhardt-Eriksson
Modelling and analysis of biological systems is crucial in order to quantitatively explain and predict their behaviour.
The importance of modelling in systems biology
becomes even more evident when tackling complex, large systems. Approaches
that rely on ...
EPFL2021