Publications

2024

• Leon Witt, Usama Zafar, KuoYeh Shen, Felix Sattler, Dan Li, Wojciech Samek
  Decentralized and Incentivized Federated Learning: A Blockchain-Enabled Framework Utilising Compressed Soft-Labels and Peer Consistency,
  IEEE Transactions on Services Computing, vol. 17, no. 4, pp. 1449-1464, July 2024, doi: 10.1109/TSC.2023.3336980, Open Access
• Daniel Becking, Karsten Müller, Paul Haase, Heiner Kirchhoffer, Gerhard Tech, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  Neural Network Coding of Difference Updates for Efficient Distributed Learning Communication,
  IEEE Transactions on Multimedia, vol. 26, pp. 6848-6863, January 2024, doi: 10.1109/TMM.2024.3357198, Open Access

2023

• David Neumann, Andreas Lutz, Karsten Müller, Wojciech Samek
  A Privacy Preserving System for Movie Recommendations using Federated Learning,
  ACM Transactions on Recommender Systems, November 2023, doi: 10.1145/3634686
• Felix Sattler, Tim Korjakow, Roman Rischke, Wojciech Samek
  FedAUX: Leveraging Unlabeled Auxiliary Data in Federated Learning,
  IEEE Transactions on Neural Networks and Learning Systems, vol. 34, no. 9, pp. 5531-5543, September 2023, doi: 10.1109/TNNLS.2021.3129371, Open Access
• Leon Witt, Mathis Heyer, Kentaroh Toyoda, Wojciech Samek, Dan Li
  Decentral and Incentivized Federated Learning Frameworks: A Systematic Literature Review,
  IEEE Internet of Things Journal, vol. 10, no. 4, pp. 3642-3663, February 2023, doi: 10.1109/JIOT.2022.3231363, Open Access
• Gayathri Venugopal, Karsten Müller, Jonathan Pfaff, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  Region-Based Template Matching Prediction for Intra Coding,
  IEEE Transactions on Image Processing, vol. 32, no. 1, pp. 779-790, January 2023, doi: 10.1109/TIP.2022.3233184, Open Access

2022

• Roman Rischke, Lisa Schneider, Karsten Müller, Wojciech Samek, Falk Schwendicke, Joachim Krois
  Federated Learning in Dentistry: Chances and Challenges,
  Journal of Dental Research, vol. 101, no. 11, pp. 1269-1273, July 2022, doi: 10.1177/00220345221108953
• Felix Sattler, Arturo Marban, Roman Rischke, Wojciech Samek
  CFD: Communication-Efficient Federated Distillation via Soft-Label Quantization and Delta Coding,
  IEEE Transactions on Network Science and Engineering, vol. 9, no. 4, pp. 2025-2038, June 2022, doi: 10.1109/TNSE.2021.3081748, Open Access
• Heiner Kirchhoffer, Paul Haase, Wojciech Samek, Karsten Müller, Hamed Rezazadegan-Tavakoli, Francesco Cricri, Emre Aksu, Miska M. Hannuksela, Wei Jiang, Wei Wang, Shan Liu, Swayambhoo Jain, Shahab Hamidi-Rad, Fabien Racape, Werner Bailer
  Overview of the Neural Network Compression and Representation (NNR) Standard,
  IEEE Transactions on Circuits and Systems for Video Technology, IEEE, vol. 32, no. 5, pp. 3203-3216, May 2022, doi: 10.1109/TCSVT.2021.3095970, Open Access

2021

• Karsten Müller, Wojciech Samek, Detlev Marpe
  Ein internationaler KI-Standard zur Kompression Neuronaler Netze,
  FKT- Fachzeitschrift für Fernsehen, Film und Elektronische Medien, pp. 33-36, September 2021
• Felix Sattler, Klaus-Robert Müller, Wojciech Samek
  Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraints,
  IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 8, pp. 3710-3722, August 2021, doi: 10.1109/TNNLS.2020.3015958, Open Access
• Simon Wiedemann, Suhas Shivapakashy, Pablo Wiedemann, Daniel Becking, Wojciech Samek, Friedel Gerfers, Thomas Wiegand
  FantastIC4: A Hardware-Software Co-Design Approach for Efficiently Running 4bit-Compact Multilayer Perceptrons,
  IEEE Open Journal of Circuits and Systems, vol. 2, pp. 407-419, May 2021, doi: 10.1109/OJCAS.2021.3083332, Open Access

2020

• Felix Sattler, Simon Wiedemann, Klaus-Robert Müller, Wojciech Samek
  Robust and Communication-Efficient Federated Learning from Non-IID Data,
  IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 9, pp. 3400-3413, September 2020, doi: 10.1109/TNNLS.2019.2944481, Open Access
• Felix Sattler, Thomas Wiegand, Wojciech Samek
  Trends and Advancements in Deep Neural Network Communication,
  ITU Journal: ICT Discoveries, vol. 3, no. 1, May 2020
• Simon Wiedemann, Heiner Kirchhoffer, Stefan Matlage, Paul Haase, Arturo Marban, Talmaj Marinc, David Neumann, Tung Nguyen, Ahmed Osman, Heiko Schwarz, Detlev Marpe, Thomas Wiegand, Wojciech Samek
  DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks,
  IEEE Journal of Selected Topics in Signal Processing, vol. 14, no. 4, pp. 700-714, May 2020, doi: 10.1109/JSTSP.2020.2969554
• Simon Wiedemann, Klaus-Robert Müller, Wojciech Samek
  Compact and Computationally Efficient Representation of Deep Neural Networks,
  IEEE Transactions on Neural Networks and Learning Systems, vol. 31, no. 3, pp. 772-785, May 2020, doi: 10.1109/TNNLS.2019.2910073

2025

• Daniel Becking, Ingo Friese, Karsten Müller, Thomas Buchholz, Mandy Galkow-Schneider, Wojciech Samek, Detlev Marpe
  Efficient Federated Learning Tiny Language Models for Mobile Network Feature Prediction,
  2025 Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit), Poznan, Poland, June 2025

2024

• Maximilian Andreas Höfler, Tatsiana Mazouka, Karsten Müller, Wojciech Samek
  Boosting Federated Learning with Diffusion Models for Non-IID and Imbalanced Data,
  IEEE International Conference on Big Data, Washington DC, USA, December 2024
• Maximilian A. Höfler, Karsten Müller, Wojciech Samek
  XAI-guided Insulator Anomaly Detection for Imbalanced Datasets,
  ECCV'24 Workshop on Vision-Based Industrial Inspection (VISION), Milan, Italy, September 2024
• Leon Witt, Armando Teles Fortes, Kentaroh Toyoda, Wojciech Samek, Dan Li
  Blockchain and Artificial Intelligence: Synergies and Conflicts,
  Proceedings of the Workshop on Blockchain and Artificial Intelligence (BCAI), Singapore, June 2024
• Leon Witt, Kentaroh Toyoda, Wojciech Samek, Dan Li
  Democratizing Federated Learning with Blockchain and Multi-Task Peer Prediction,
  Proceedings of the Workshop on Blockchain and Artificial Intelligence (BCAI), Singapore, June 2024

2023

• Daniel Becking, Paul Haase, Heiner Kirchhoffer, Karsten Müller, Wojciech Samek, Detlev Marpe
  NNCodec: An Open Source Software Implementation of the Neural Network Coding ISO/IEC Standard,
  ICML'23 Workshop on Neural Compression, Hawaii, USA, July 2023

2022

• Gerhard Tech, Paul Haase, Daniel Becking, Heiner Kirchhoffer, Karsten Müller, Jonathan Pfaff, Heiko Schwarz, Wojciech Samek, Detlev Marpe, Thomas Wiegand
  History Dependent Significance Coding for Incremental Neural Network Compression,
  IEEE International Conference on Image Processing (ICIP), Bordeaux, France, pp. 3541-3545, October 2022, doi: 10.1109/ICIP46576.2022.9897825
• Daniel Becking, Heiner Kirchhoffer, Gerhard Tech, Paul Haase, Karsten Müller, Heiko Schwarz, Wojciech Samek
  Adaptive Differential Filters for Fast and Communication-Efficient Federated Learning,
  IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), New Orleans, USA, pp. 3366-3375, June 2022, doi: 10.1109/CVPRW56347.2022.00380

2021

• Paul Haase, Daniel Becking, Heiner Kirchhoffer, Karsten Müller, Heiko Schwarz, Wojciech Samek, Detlev Marpe, Thomas Wiegand
  Encoder Optimizations for the NNR Standard on Neural Network Compression,
  Proceedings of the IEEE International Conference on Image Processing (ICIP), Anchorage, AK, USA, pp. 3522-3526, September 2021, doi: 10.1109/ICIP42928.2021.9506655

2020

• Paul Haase, Heiko Schwarz, Heiner Kirchhoffer, Simon Wiedemann, Talmaj Marinc, Arturo Marban, Karsten Müller, Wojciech Samek, Detlev Marpe, Thomas Wiegand
  Dependent Scalar Quantization for Neural Network Compression,
  Proceedings of the IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates, pp. 36-40, July 2020, doi: 10.1109/ICIP40778.2020.9190955
• David Neumann, Felix Sattler, Heiner Kirchhoffer, Simon Wiedemann, Karsten Müller, Heiko Schwarz, Thomas Wiegand, Detlev Marpe, Wojciech Samek
  DeepCABAC: Plug&Play Compression of Neural Network Weights and Weight Updates,
  Proceedings of the IEEE International Conference on Image Processing (ICIP), Abu Dhabi, United Arab Emirates, pp. 21-25, July 2020, doi: 10.1109/ICIP40778.2020.9190821
• Simon Wiedemann, Temesgen Mehari, Kevin Kepp, Wojciech Samek
  Dithered backprop: A sparse and quantized backpropagation algorithm for more efficient deep neural network training,
  Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA, pp. 3096-3104, June 2020, doi: 10.1109/CVPRW50498.2020.00368
• Arturo Marban, Daniel Becking, Simon Wiedemann, Wojciech Samek
  Learning Sparse & Ternary Neural Networks with Entropy-Constrained Trained Ternarization (EC2T),
  Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA, pp. 3105-3113, June 2020, doi: 10.1109/CVPRW50498.2020.00369
• Felix Sattler, Klaus-Robert Müller, Thomas Wiegand, Wojciech Samek
  On the Byzantine Robustness of Clustered Federated Learning,
  IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, pp. 8861-8865, May 2020, doi: 10.1109/ICASSP40776.2020.9054676

2019

• Felix Sattler, Klaus-Robert Müller, Wojciech Samek
  Clustered Federated Learning,
  NeurIPS'19 Workshop on Federated Learning for Data Privacy and Confidentiality, Vancouver, Canada, December 2019
• Felix Sattler, Simon Wiedemann, Klaus-Robert Müller, Wojciech Samek
  Sparse Binary Compression: Towards Distributed Deep Learning with minimal Communication,
  IEEE International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, pp. 1-8, July 2019, doi: 10.1109/IJCNN.2019.8852172
• Simon Wiedemann, Arturo Marban, Klaus-Robert Müller, Wojciech Samek
  Entropy-Constrained Training of Deep Neural Networks,
  IEEE International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, pp. 1-8, July 2019, doi: 10.1109/IJCNN.2019.8852119
• Simon Wiedemann, Heiner Kirchhoffer, Stefan Matlage, Paul Haase, Arturo Marban, Talmaj Marinc, Heiko Schwarz, Detlev Marpe, Thomas Wiegand, Ahmed Osman, Wojciech Samek
  DeepCABAC: Context-adaptive binary arithmetic coding for deep neural network compression,
  International Conference on Machine Learning, Joint ICML’19 Workshop on On-Device Machine Learning & Compact Deep Neural Network Representations (ODML-CDNNR), Long Beach, CA, USA, June 2019, Best Paper Award

2018

• Simon Wiedemann, Klaus-Robert Müller, Wojciech Samek
  Compact and Computationally Efficient Representation of Deep Neural Networks,
  NIPS Workshop on Compact Deep Neural Network Representation with Industrial Applications (CDNNRIA), Montreal, Canada, pp. 1-6, December 2018
• Christopher Ehmann, Wojciech Samek
  Transferring Information between Neural Networks,
  Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Calgary, Canada, pp. 2361-2365, April 2018, doi: 10.1109/ICASSP.2018.8461511

2025

• Daniel Becking, Karsten Müller
  [NNC] EE1.2 on Low Overhead Gradients and Activations Coding for Split Learning,
  ISO/IEC JTC1/SC29/WG4/m71127, January 2025

2024

• Daniel Becking, Karsten Müller, Paul Haase, Gerhard Tech
  [NNC] Updates to Reference Software for Conformance Bitstreams and Draft Text of FDIS ISO/IEC 15938-18ed2,
  ISO/IEC JTC1/SC29/WG04/m68827, July 2024
• Daniel Becking, Karsten Müller, Paul Haase, Gerhard Tech, Heiner Kirchhoffer, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNC] Initial Insights into Coding Large Language Models (LLMs) with NNCodec,
  ISO/IEC JTC1/SC29/WG04/m66483, January 2024

2023

• David Neumann, Andreas Lutz, Karsten Müller, Wojciech Samek
  [NNC] Neural Network Coding in Recommender System Use Case,
  ISO/IEC JTC1/SC29/WG04/m59331, April 2023
• Heiner Kirchhoffer, Paul Haase, Daniel Becking, Gerhard Tech, Karsten Müller, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNC] Bug report on CABAC entry point signaling in ISO/IEC FDIS 15938-17 edition 1,
  ISO/IEC JTC1/SC29/WG04/m63092, April 2023
• Paul Haase, Daniel Becking, Heiner Kirchhoffer, Gerhard Tech, Karsten Müller, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNC] NNCodec: An open NNC encoder/decoder implementation,
  ISO/IEC JTC1/SC29/WG04/m61972, January 2023

2022

• Paul Haase, Heiner Kirchhoffer, Gerhard Tech, Daniel Becking, Karsten Müller, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNC] Clarification on colocated context derivation for temporal context modeling,
  ISO/IEC JTC1/SC29/WG04/m61115, October 2022
• David Neumann, Karsten Müller, Wojciech Samek
  [NNC] Neural Network Coding in Recommender System Use Case,
  ISO/IEC JTC1/SC29/WG04/m59331, April 2022
• Karsten Müller, Heiner Kirchhoffer, Paul Haase, Daniel Becking, Gerhard Tech, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNC] Communication Patterns in Federated Learning utilizing PUT,
  ISO/IEC JTC1/SC29/WG04/m59504, April 2022
• Paul Haase, Heiner Kirchhoffer, Karsten Müller, Daniel Becking, Gerhard Tech, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNC] Tensor dimension reordering by tensor dimension shift,
  ISO/IEC JTC1/SC29/WG04/m59534, April 2022
• Daniel Becking, Paul Haase, Heiner Kirchhoffer, Gerhard Tech, Karsten Müller, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNC] BatchNorm Folding Update for ICNN,
  ISO/IEC JTC1/SC29/WG04/m59535, April 2022
• Gerhard Tech, Paul Haase, Heiner Kirchhoffer, Daniel Becking, Karsten Müller, Heiko Schwarz, Jonathan Pfaff, Wojciech Samek, Detlev Marpe, Thomas Wiegand
  [NNC] CE3-related: History Dependent Significance Probability Derivation,
  ISO/IEC JTC1/SC29/WG04/m58810, January 2022
• Paul Haase, Heiner Kirchhoffer, Karsten Müller, Daniel Becking, Gerhard Tech, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNC] CE3-related: CABAC adaptation for binary/ternary codebooks,
  ISO/IEC JTC1/SC29/WG04/m58848, January 2022
• Daniel Becking, Paul Haase, Heiner Kirchhoffer, Gerhard Tech, Karsten Müller, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNC] General Local Scaling Adaptation with Warm Restarts for Incremental Neural Network Compression,
  ISO/IEC JTC1/SC29/WG04/m58821, January 2022
• Daniel Becking, Paul Haase, Heiner Kirchhoffer, Gerhard Tech, Karsten Müller, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNC] V1-V2-Harmonized and Revised Test Model Software of ICNN,
  ISO/IEC JTC1/SC29/WG04/m58825, January 2022

2021

• Karsten Müller, Paul Haase, Heiner Kirchhoffer, Daniel Becking, Gerhard Tech, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNR] Naming Proposal "Neural Network Coding – NNC" for ISO/IEC 15938-17,
  ISO/IEC JTC1/SC29/WG04/m58067, October 2021
• Paul Haase, Heiner Kirchhoffer, Karsten Müller, Daniel Becking, Gerhard Tech, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNR] Conformance Bitstreams for ISO/IEC 15938-18,
  ISO/IEC JTC1/SC29/WG04/m58093, October 2021
• Paul Haase, Heiner Kirchhoffer, Karsten Müller, Daniel Becking, Gerhard Tech, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNR] Error report on ISO/IEC FDIS 15938-17 and proposed solutions,
  ISO/IEC JTC1/SC29/WG04/m58247, October 2021
• Daniel Becking, Paul Haase, Heiner Kirchhoffer, Gerhard Tech, Karsten Müller, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNR] CE1: Report on HHI Results for Incremental Neural Network Compression,
  ISO/IEC JTC1/SC29/WG04/m58068, October 2021
• Paul Haase, Heiner Kirchhoffer, Daniel Becking, Gerhard Tech, Karsten Müller, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNR] CE1-CE3: Report on HHI Results for Incremental Neural Network Compression,
  ISO/IEC JTC1/SC29/WG4/m57416, July 2021
• Heiner Kirchhoffer, Karsten Müller, Detlev Marpe, Heiko Schwarz, Thomas Wiegand
  [NNR] Batch norm unfolding clarification for DIS of ISO/IEC 15938-17,
  ISO/IEC JTC1/SC29/WG4 MPEG2021/m56748, April 2021
• Heiner Kirchhoffer, Daniel Becking, Karsten Müller, Detlev Marpe, Heiko Schwarz, Thomas Wiegand
  [NNR] Generic topology storage format for DIS of ISO/IEC 15938-17,
  ISO/IEC JTC1/SC29/WG4 MPEG2021/m56813, April 2021
• Daniel Becking, Paul Haase, Gerhard Tech, Heiner Kirchhoffer, Karsten Müller, Heiko Schwarz, Wojciech Samek, Detlev Marpe, Thomas Wiegand
  [NNR] Response to the Call for Proposals on incremental compression of neural networks for multimedia content description and analysis,
  ISO/IEC JTC1/SC29/WG4 MPEG2021/m56621, April 2021

2020

• Paul Haase, Daniel Becking, Heiner Kirchhoffer, Karsten Müller, Wojciech Samek, Detlev Marpe, Heiko Schwarz, Thomas Wiegand
  [NNR] CE4 method 19: Results on QP optimizations,
  ISO/IEC JTC1/SC29/WG4 MPEG2020/m55073, online meeting, October 2020
• Heiner Kirchhoffer, Karsten Müller, Wojciech Samek, Detlev Marpe, Heiko Schwarz, Thomas Wiegand
  [NNR] Committee draft cleanups, improvements, and bug fixes,
  ISO/IEC JTC1/SC29/WG4 MPEG2020/m55068, online meeting, October 2020
• Heiner Kirchhoffer, Paul Haase, Karsten Müller, Detlev Marpe, Heiko Schwarz, Thomas Wiegand
  [NNR] HLS for parallel CABAC decoding including parameter optimizations,
  online meeting, ISO/IEC JTC1/SC29/WG4 MPEG2020/m55066, October 2020
• Heiner Kirchhoffer, Karsten Müller, Detlev Marpe, Heiko Schwarz, Thomas Wiegand
  [NNR] Harmonization of codebook quantization and NNR_PT_BLOCK compressed data payload type,
  online meeting, ISO/IEC JTC1/SC29/WG4 MPEG2020/m55575, October 2020
• Daniel Becking, Heiner Kirchhoffer, Karsten Müller, Wojciech Samek, Detlev Marpe, Heiko Schwarz, Thomas Wiegand
  [NNR] HLS for additional framework support,
  ISO/IEC JTC1/SC29/WG4 MPEG2020/m55067, online meeting, October 2020
• Heiner Kirchhoffer, Paul Haase, Simon Wiedemann, Talmaj Marinc, Karsten Müller, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNR] CE4: Results on parameter optimization for DeepCABAC (method 18) and local scaling adaptation (method 19),
  online meeting, ISO/IEC JTC1/SC29/WG11 MPEG2020/m54395, July 2020
• Paul Haase, Heiner Kirchhoffer, Karsten Müller, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNR]: HLS adaptation for integer codebook representation,
  online meeting, ISO/IEC JTC1/SC29/WG11 MPEG2020/m54397, July 2020
• Heiner Kirchhoffer, Karsten Müller, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  [NNR]: Low-rank decomposition syntax for NNR compressed payload type NNR_PT_BLOCK_LS on top of m54395,
  online meeting, ISO/IEC JTC1/SC29/WG11 MPEG2020/m54806, July 2020
• Heiner Kirchhoffer, Paul Haase, Simon Wiedemann, Talmaj Marinc, Karsten Müller, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  CE4: Results on parameter optimization for DeepCABAC (method 18) and local scaling adaptation (method 19),
  ISO/IEC JTC1/SC29/WG11 MPEG2020/m54395, Online Meeting, June 2020
• Karsten Müller, Heiner Kirchhoffer, Talmaj Marinc, Simon Wiedemann, Heiko Schwarz, Wojciech Samek, Detlev Marpe, Thomas Wiegand
  Additional HLS and decoding process specification for Neural Network Compression (ISO/IEC 15938-17),
  ISO/IEC JTC1/SC29/WG11 MPEG2020/m53518, Alpbach, Austria, April 2020
• Simon Wiedemann, Paul Haase, Heiner Kirchhoffer, Talmaj Marinc, Karsten Müller, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  CE2-CE3-related: Local parameter scaling,
  ISO/IEC JTC1/SC29/WG11 MPEG2020/m53517, Alpbach, Austria, April 2020
• Simon Wiedemann, Paul Haase, Heiner Kirchhoffer, Talmaj Marinc, Karsten Müller, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  Results on importance-weighted quantization,
  ISO/IEC JTC1/SC29/WG11 MPEG2020/m53516, Alpbach, Austria, April 2020
• Paul Haase, Heiner Kirchhoffer, Simon Wiedemann, Talmaj Marinc, Karsten Müller, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  CE3-related: Parameter-Optimization for DeepCABAC,
  ISO/IEC JTC1/SC29/WG11 MPEG2020/m53515, Alpbach, Austria, April 2020
• Paul Haase, Heiner Kirchhoffer, Simon Wiedemann, Talmaj Marinc, Karsten Müller, Wojciech Samek, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
  CE2-CE3: Results on dependent scalar quantization,
  ISO/IEC JTC1/SC29/WG11 MPEG2020/m53514, Alpbach, Austria, April 2020
• Paul Haase, Heiko Schwarz, Heiner Kirchhoffer, Simon Wiedemann, Stefan Matlage, Talmaj Marinc, Arturo Marban, Karsten Müller, Wojciech Samek, Detlev Marpe, Thomas Wiegand
  CE2-related: Dependent scalar quantization for neural network parameter approximation,
  ISO/IEC JTC1/SC29/WG11 MPEG2020/m52358, Brussels, Belgium, January 2020
• Karsten Müller, Robert Skupin, Yago Sanchez de la Fuente, Simon Wiedemann, Heiner Kirchhoffer, Heiko Schwarz, Wojciech Samek, Detlev Marpe, Thomas Wiegand
  Basic High-Level Syntax for Neural Network Compression (ISO/IEC 15938-17, i.e. MPEG-7 part 17),
  ISO/IEC JTC1/SC29/WG11 MPEG2020/m52352, Brussels, Belgium, January 2020
• Felix Sattler, David Neumann, Simon Wiedemann, Karsten Müller, Wojciech Samek, Detlev Marpe, Thomas Wiegand
  Test Data, Evaluation Framework and Results for NNU / Federated Learning Use Cases,
  ISO/IEC JTC1/SC29/WG11 MPEG2020/m52375, Brussels, Belgium, January 2020

2019

• Simon Wiedemann, Heiner Kirchhoffer, Wojciech Samek, Karsten Müller, Detlev Marpe, Heiko Schwarz, Thomas Wiegand
  Proposal of python interfaces for an NNR test model,
  ISO/IEC JTC1/SC29/WG11 MPEG2019/M49867, Gothenburg, Sweden, July 2019
• Simon Wiedemann, Heiner Kirchhoffer, Stefan Matlage, Paul Haase, Arturo Marban, Talmaj Marinc, David Neumann, Heiko Schwarz, Detlev Marpe, Wojciech Samek, Thomas Wiegand
  Report of CEs results,
  ISO/IEC JTC1/SC29/WG11 MPEG2019/m48662, Gothenburg, Sweden, July 2019
• Simon Wiedemann, Heiner Kirchhoffer, Stefan Matlage, Paul Haase, Arturo Marban, Talmaj Marinc, David Neumann, Ahmed Osman, Heiko Schwarz, Detlev Marpe, Wojciech Samek, Thomas Wiegand
  Response to the Call for Proposals on Neural Network Compression: End-to-end processing pipeline for highly compressible neural networks,
  ISO/IEC JTC1/SC29/WG11 MPEG2019/M47698, Geneva, Switzerland, March 2019

2018

• Wojciech Samek, Simon Wiedemann
  Efficient representations of neural networks,
  ITU-T FG-ML5G-I-102, Tokyo, Japan, November 2018

2017

• Wojciech Samek, Simon Wiedemann, Slawomir Stanczak, Thomas Wiegand
  Data Formats and Specifications for Efficient Machine Learning in Communications,
  ITU-T FG-ML5G-I-013, Geneva, Switzerland, January 2017

2023

• Wojciech Samek
  The New ISO/IEC Standard for Neural Network Coding,
  ECML PKDD'23 Workshop on "Simplification, Compression, Efficiency and Frugality for Artificial intelligence", Torino, Italy, September 2023, Talk

2022

• Wojciech Samek
  Towards Communication-Efficient and Personalized Federated Learning,
  2021 IEEE SPS Cycle 2 School on Networked Federated Learning: Theory, Algorithms and Applications, virtual event, April 2022, Talk

2021

• Wojciech Samek
  Wireless Federated Learning,
  IEEE SPAWC, Lucca, Italy, September 2021, Tutorial, Talk

2020

• Wojciech Samek
  DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks,
  Workshop on Energy Efficient Machine Learning and Cognitive Computing, online event, December 2020, Talk
• Wojciech Samek
  Distributed Deep Learning: Concepts, Methods & Applications in Wireless Networks,
  IEEE GLOBECOM, Taipei, Taiwan, December 2020, Tutorial, Talk
• Wojciech Samek
  A Universal Compression Algorithm for Deep Neural Networks,
  AI for Good Global Summit 2020, Geneva, Switzerland, August 2020, Talk
• Wojciech Samek, Felix Sattler
  Distributed and Efficient Deep Learning,
  IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, May 2020, Tutorial, Invited Talk
• Wojciech Samek
  Robust and Communication-Efficient Federated Learning,
  Workshop "Sensor AI", Berlin, Germany, April 2020, Talk
• Wojciech Samek
  Recent Advances in Federated Learning for Communication,
  ITU AI/ML in 5G Challenge, virtual event, 2020, Talk

2019

• Wojciech Samek
  Federated Learning and its Applications in Communications,
  AI for 5G & Beyond Day, Berlin, Germany, November 2019, Talk
• Wojciech Samek
  Compression of Deep Neural Networks,
  ITU Workshop, The future of media, Geneva, Switzerland, October 2019, Talk

2018

• Wojciech Samek
  Interpretable, Efficient and Distributed Deep Learning,
  Fritz Haber Institute, Seminar, Berlin, Germany, July 2018, Talk
• Wojciech Samek
  Efficient, Distributed and Interpretable Deep Learning,
  ITU Workshop on "Impact of AI on ICT Infrastructures", Xi'an, China, April 2018, Invited Talk
• Wojciech Samek
  Efficient and Interpretable Deep Learning,
  Forum Digital Transformation: The impacts of Artificial Intelligence on Economy, Berlin, Germany, March 2018, Talk
• Wojciech Samek
  Komplexitätsreduzierte Algorithmen des Maschinellen Lernens,
  Fraunhofer-Symposium "Netzwert", Munich, Germany, February 2018, Invited Talk
• Wojciech Samek
  Efficient Deep Learning in Communications,
  ITU Workshop on "Machine Learning for 5G and beyond", Geneva, Switzerland, January 2018, Invited Talk

2023

• Haley Hoech, Roman Rischke, Karsten Müller, Wojciech Samek
  FedAUXfdp: Differentially Private One-Shot Federated Distillation,
  In: Trustworthy Federated Learning, Lecture Notes in Computer Science, Springer International Publishing, Cham, Switzerland, vol. 13448, pp. 100-114, March 2023, doi: 10.1007/978-3-031-28996-5_8, Book Chapter

2022

• Daniel Becking, Maximilian Dreyer, Wojciech Samek, Karsten Müller, Sebastian Lapuschkin
  ECQx: Explainability-Driven Quantization for Low-Bit and Sparse DNNs,
  In: xxAI - Beyond Explainable AI, LNAI, Springer, Cham, vol. 13200, pp. 271-296, April 2022, doi: 10.1007/978-3-031-04083-2_14, Book Chapter

to top