Felix Sattler - IEEE Xplore Author Profile
Subscribe
ADVANCED SEARCH

Author details

< Back

Felix Sattler

Publications
8
Citations
1,843
Publications by Year
20192024
Co-Authors:
Show All Co-Authors (17)
Image of author Felix Sattler

Felix Sattler

Affiliation

Department of Artificial Intelligence
Fraunhofer Heinrich Hertz Institute
Berlin, Germany

Publication Topics

Biography

Felix Sattler received the BSc degree in mathematics, in 2016, the MSc degree in computer science, in 2018, the MSc degree in applied mathematics, in 2018, all from Technische Universität Berlin, and the PhD degree with distinction from the Technical University of Berlin, in 2021. His research interests include efficient and robust machine learning, federated learning and multi-task learning.(Based on document published on 28 November 2023).
Publications
8
Citations
1,843
Publications by Year
20192024
Co-Authors:
Show All Co-Authors (17)
Author's Published Works

Showing 1-8 of 8 results

  • Sort

Filter Results

Show

Sort By

Results

Decentralized and Incentivized Federated Learning: A Blockchain-Enabled Framework Utilising Compressed Soft-Labels and Peer Consistency

Leon Witt;Usama Zafar;KuoYeh Shen;Felix Sattler;Dan Li;Songtao Wang;Wojciech Samek

IEEE Transactions on Services Computing
Year: 2024 | Volume: 17, Issue: 4 | Journal Article |
Cited by: Papers (2)
Federated Learning (FL) has emerged as a powerful paradigm in Artificial Intelligence, facilitating the parallel training of Artificial Neural Networks on edge devices while safeguarding data privacy. Nonetheless, to encourage widespread adoption, Federated Learning Frameworks (FLFs) must tackle (i) the power imbalance between a central authority and its participants, and (ii) the challenge of equ...Show More

Decentralized and Incentivized Federated Learning: A Blockchain-Enabled Framework Utilising Compressed Soft-Labels and Peer Consistency

Leon Witt;Usama Zafar;KuoYeh Shen;Felix Sattler;Dan Li;Songtao Wang;Wojciech Samek

Year: 2024 | Volume: 17, Issue: 4 | Journal Article |

FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learning

Felix Sattler;Tim Korjakow;Roman Rischke;Wojciech Samek

IEEE Transactions on Neural Networks and Learning Systems
Year: 2023 | Volume: 34, Issue: 9 | Journal Article |
Cited by: Papers (57)
Federated distillation (FD) is a popular novel algorithmic paradigm for Federated learning (FL), which achieves training performance competitive to prior parameter averaging-based methods, while additionally allowing the clients to train different model architectures, by distilling the client predictions on an unlabeled auxiliary set of data into a student model. In this work, we propose FedAUX, a...Show More

FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learning

Felix Sattler;Tim Korjakow;Roman Rischke;Wojciech Samek

Year: 2023 | Volume: 34, Issue: 9 | Journal Article |

CFD: Communication-Efficient Federated Distillation via Soft-Label Quantization and Delta Coding

Felix Sattler;Arturo Marban;Roman Rischke;Wojciech Samek

IEEE Transactions on Network Science and Engineering
Year: 2022 | Volume: 9, Issue: 4 | Journal Article |
Cited by: Papers (33)
Communication constraints are one of the majorchallenges preventing the wide-spread adoption of Federated Learning systems. Recently, Federated Distillation (FD), a new algorithmic paradigm for Federated Learning with fundamentally different communication properties, emerged. FD methods leverage ensemble distillation techniques and exchange model outputs, presented as soft labels on an unlabeled p...Show More

CFD: Communication-Efficient Federated Distillation via Soft-Label Quantization and Delta Coding

Felix Sattler;Arturo Marban;Roman Rischke;Wojciech Samek

Year: 2022 | Volume: 9, Issue: 4 | Journal Article |

Clustered Federated Learning: Model-Agnostic Distributed Multitask Optimization Under Privacy Constraints

Felix Sattler;Klaus-Robert Müller;Wojciech Samek

IEEE Transactions on Neural Networks and Learning Systems
Year: 2021 | Volume: 32, Issue: 8 | Journal Article |
Cited by: Papers (570)
Federated learning (FL) is currently the most widely adopted framework for collaborative training of (deep) machine learning models under privacy constraints. Albeit its popularity, it has been observed that FL yields suboptimal results if the local clients’ data distributions diverge. To address this issue, we present clustered FL (CFL), a novel federated multitask learning (FMTL) framework, whic...Show More

Clustered Federated Learning: Model-Agnostic Distributed Multitask Optimization Under Privacy Constraints

Felix Sattler;Klaus-Robert Müller;Wojciech Samek

Year: 2021 | Volume: 32, Issue: 8 | Journal Article |

Deepcabac: Plug & Play Compression of Neural Network Weights and Weight Updates

David Neumann;Felix Sattler;Heiner Kirchhoffer;Simon Wiedemann;Karsten Müller;Heiko Schwarz;Thomas Wiegand;Detlev Marpe;Wojciech Samek

2020 IEEE International Conference on Image Processing (ICIP)
Year: 2020 | Conference Paper |
Cited by: Papers (5)
An increasing number of distributed machine learning applications require efficient communication of neural network parameterizations. DeepCABAC, an algorithm in the current working draft of the emerging MPEG-7 part 17 standard for compression of neural networks for multimedia content description and analysis, has demonstrated high compression gains for a variety of neural network models. In this ...Show More

Deepcabac: Plug & Play Compression of Neural Network Weights and Weight Updates

David Neumann;Felix Sattler;Heiner Kirchhoffer;Simon Wiedemann;Karsten Müller;Heiko Schwarz;Thomas Wiegand;Detlev Marpe;Wojciech Samek

Year: 2020 | Conference Paper |

On the Byzantine Robustness of Clustered Federated Learning

Felix Sattler;Klaus-Robert Müller;Thomas Wiegand;Wojciech Samek

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Year: 2020 | Conference Paper |
Cited by: Papers (92)
Federated Learning (FL) is currently the most widely adopted framework for collaborative training of (deep) machine learning models under privacy constraints. Albeit it's popularity, it has been observed that Federated Learning yields suboptimal results if the local clients' data distributions diverge. The recently proposed Clustered Federated Learning Framework addresses this issue, by separating...Show More

On the Byzantine Robustness of Clustered Federated Learning

Felix Sattler;Klaus-Robert Müller;Thomas Wiegand;Wojciech Samek

Year: 2020 | Conference Paper |

Robust and Communication-Efficient Federated Learning From Non-i.i.d. Data

Felix Sattler;Simon Wiedemann;Klaus-Robert Müller;Wojciech Samek

IEEE Transactions on Neural Networks and Learning Systems
Year: 2020 | Volume: 31, Issue: 9 | Journal Article |
Cited by: Papers (954)
Federated learning allows multiple parties to jointly train a deep learning model on their combined data, without any of the participants having to reveal their local data to a centralized server. This form of privacy-preserving collaborative learning, however, comes at the cost of a significant communication overhead during training. To address this problem, several compression methods have been ...Show More

Robust and Communication-Efficient Federated Learning From Non-i.i.d. Data

Felix Sattler;Simon Wiedemann;Klaus-Robert Müller;Wojciech Samek

Year: 2020 | Volume: 31, Issue: 9 | Journal Article |

Sparse Binary Compression: Towards Distributed Deep Learning with minimal Communication

Felix Sattler;Simon Wiedemann;Klaus-Robert Müller;Wojciech Samek

2019 International Joint Conference on Neural Networks (IJCNN)
Year: 2019 | Conference Paper |
Cited by: Papers (130)
Currently, progressively larger deep neural networks are trained on ever growing data corpora. In result, distributed training schemes are becoming increasingly relevant. A major issue in distributed training is the limited communication bandwidth between contributing nodes or prohibitive communication cost in general. To mitigate this problem we propose Sparse Binary Compression (SBC), a compress...Show More

Sparse Binary Compression: Towards Distributed Deep Learning with minimal Communication

Felix Sattler;Simon Wiedemann;Klaus-Robert Müller;Wojciech Samek

Year: 2019 | Conference Paper |

IEEE Account

Purchase Details

Profile Information

Need Help?

A not-for-profit organization, IEEE is the world's largest technical professional organization dedicated to advancing technology for the benefit of humanity.
© Copyright 2025 IEEE - All rights reserved. Use of this web site signifies your agreement to the terms and conditions.