activity
20182023
most citedCommunication-Efficient Federated Distillation

13 citations · 15 across the 4 of their papers we have counts for

collaborators

8 papers

cs.LG20212 cited

Reward-Based 1-bit Compressed Federated Distillation on Blockchain

Leon Witt, Usama Zafar, KuoYeh Shen +3

The recent advent of various forms of Federated Knowledge Distillation (FD) paves the way for a new generation of robust and communication-efficient Federated Learning (FL), where…

cs.LG2021

FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learning

Felix Sattler, Tim Korjakow, Roman Rischke +1

Federated Distillation (FD) is a popular novel algorithmic paradigm for Federated Learning, which achieves training performance competitive to prior parameter averaging based metho…

cs.LG202013 cited

Communication-Efficient Federated Distillation

Felix Sattler, Arturo Marban, Roman Rischke +1

Communication constraints are one of the major challenges preventing the wide-spread adoption of Federated Learning systems. Recently, Federated Distillation (FD), a new algorithmi…

q-bio.QM2020

Risk Estimation of SARS-CoV-2 Transmission from Bluetooth Low Energy Measurements

Felix Sattler, Jackie Ma, Patrick Wagner +6

Digital contact tracing approaches based on Bluetooth low energy (BLE) have the potential to efficiently contain and delay outbreaks of infectious diseases such as the ongoing SARS…

cs.LG2020

Trends and Advancements in Deep Neural Network Communication

Felix Sattler, Thomas Wiegand, Wojciech Samek

Due to their great performance and scalability properties neural networks have become ubiquitous building blocks of many applications. With the rise of mobile and IoT, these models…

cs.LG2019

Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints

Felix Sattler, Klaus-Robert Müller, Wojciech Samek

Federated Learning (FL) is currently the most widely adopted framework for collaborative training of (deep) machine learning models under privacy constraints. Albeit it's popularit…