David Neumann, M.Sc.
PhD Candidate and Research Associate in Machine Learning
working at the
Fraunhofer HHI, Berlin, Germany
in the
Artificial Intelligence Department
Publications

Software for dataset-wide XAI: From local explanations to global insights with Zennit, CoRelAy, and ViRelAy
January 2, 2026
Christopher J. Anders*, David Neumann*, Wojciech Samek, Klaus-Robert Müller, and Sebastian Lapuschkin (*equal contribution)
Published in PLOS ONE, volume 21, number 1.

A Privacy Preserving System for Movie Recommendations Using Federated Learning
November 27, 2024
David Neumann, Andreas Lutz, Karsten Müller, and Wojciech Samek
Published in the special issue 3, number 2, “Trustworthy Recommender Systems” of the ACM Transactions on Recommender Systems (TORS) journal.

Finding and Removing Clever Hans: Using Explanation Methods to Debug and Improve Deep Models
August 3, 2021
Christopher J. Anders, Leander Weber, David Neumann, Wojciech Samek, Klaus-Robert Müller, and Sebastian Lapuschkin
Published in Elsevier Information Fusion, volume 77.

Risk estimation of SARS-CoV-2 transmission from bluetooth low energy measurements
October 6, 2020
Felix Sattler, Jackie Ma, Patrick Wagner, David Neumann, Markus Wenzel, Ralf Schäfer, Wojciech Samek, Klaus-Robert Müller, and Thomas Wiegand
Published in Nature npj Digital Medicine, volume 3, number 1.

DeepCABAC: Plug&Play Compression of Neural Network Weights and Weight Updates
September 30, 2020
David Neumann, Felix Sattler, Heiner Kirchhoffer, Simon Wiedemann, Karsten Müller, Heiko Schwarz, Thomas Wiegand, Detlev Marpe, and Wojciech Samek
Published in the Proceedings of the 2020 IEEE International Conference on Image Processing (ICIP).

XAI for Analyzing and Unlearning Spurious Correlations in ImageNet
July 17, 2020
Christopher J. Anders, David Neumann, Talmaj Marinč, Wojciech Samek, Klaus-Robert Müller, and Sebastian Lapuschkin
Presented at the Extending Explainable AI Beyond Deep Models and Classifiers Workshop (XXAI) at the 2020 International Conference on Machine Learning (ICML).

DeepCABAC: A Universal Compression Algorithm for Deep Neural Networks
January 27, 2020
Simon Wiedemann, Heiner Kirchhoffer, Stefan Matlage, Paul Haase, Arturo Marbán González, Talmaj Marinč, David Neumann, Tung Nguyen, Heiko Schwarz, Thomas Wiegand, Detlev Marpe, and Wojciech Samek
Published in IEEE Journal of Selected Topics in Signal Processing, volume 14, number 4.

DeepCABAC: Context-adaptive binary arithmetic coding for deep neural network compression
January 27, 2020
Simon Wiedemann, Heiner Kirchhoffer, Stefan Matlage, Paul Haase, Arturo Marbán González, Talmaj Marinč, David Neumann, Tung Nguyen, Heiko Schwarz, Thomas Wiegand, Detlev Marpe, and Wojciech Samek
Published in IEEE Journal of Selected Topics in Signal Processing, volume 14, number 4.
Talks

DeepCABAC: Plug&Play Compression of Neural Network Weights and Weight Updates
Monday, October 26, 2020, 12:00 - 12:25 (Abu Dhabi, Gulf Standard Time)
2020 International Conference on Image Processing (ICIP)