Publications associées à Client léger

Federated learning with uncertainty-based client clustering for fleet-wide fault diagnosis

Operators from various industries have been pushing the adoption of wireless sensing nodes for industrial monitoring, and such efforts have produced sizeable condition monitoring datasets that can be used to build diagnosis algorithms capable of warning ma ...

2024

Personalized 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 ...

2023

Bridging the gap between theoretical and practical privacy technologies for at-risk populations

Kasra Edalatnejadkhamene

With the pervasive digitalization of modern life, we benefit from efficient access to information and services. Yet, this digitalization poses severe privacy challenges, especially for special-needs individuals. Beyond being a fundamental human right, priv ...

EPFL2023

Groove: Flexible Metadata-Private Messaging

Ludovic Barman, David Lazar

Metadata-private messaging designs that scale to support millions of users are rigid: they limit users to a single device that is online all the time and transmits on short regular intervals, and require users to choose precisely when each of their buddies ...

Usenix Assoc2022

Quasi-Global Momentum: Accelerating Decentralized Deep Learning on Heterogeneous Data

Martin Jaggi, Tao Lin, Sebastian Urban Stich, 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 RESEARCH2021

The Performance of Byzantine Fault Tolerant Blockchains

Vincent Gramoli

Blockchains have captured the attention of many, resulting in an abundance of new systems available for use. However, selecting an appropriate blockchain for an application is challenging due to the lack of comparative information discussing core metrics s ...

IEEE2020

Ensemble Distillation for Robust Model Fusion in Federated Learning

Martin Jaggi, Sebastian Urban Stich, Tao Lin, Lingjing Kong

Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model while keeping the training data decentralized. In most of the current training schemes the central model is refined by averaging the par ...

2020

DynaBurst: Dynamically Assemblying DRAM Bursts over a Multitude of Random Accesses

Paolo Ienne, Mikhail Asiatici

The effective bandwidth of the FPGA external memory, usually DRAM, is extremely sensitive to the access pattern. Nonblocking caches that handle thousands of outstanding misses (miss-optimized memory systems) can dynamically improve bandwidth utilization wh ...

IEEE2019

Load Balancing Video Clients in Enterprise Wireless Networks

Dan-Cristian Tomozei, Lorenzo Granai, Aswin Suresh, Sergio Mena

Given the increasing popularity of real-time video communication over enterprise wireless networks, ensuring good quality of experience is becoming critical. A common problem in such networks is that the clients typically adopt the strategy of associating ...

IEEE2018

Towards a Solution to the Red Wedding Problem

Heather Christine Klug

Edge computing promises lower latency interactions for clients operating at the edge by shifting computation away from Data Centers to Points of Presence which are more abundant and located geographically closer to end users. However, most commercially ava ...

2018