no code implementations • 28 Sep 2023 • David Jin, Niclas Kannengießer, Sascha Rank, Ali Sunyaev
Various collaborative distributed machine learning (CDML) systems, including federated learning systems and swarm learning systems, with different key traits were developed to leverage resources for development and use of machine learning (ML) models in a confidentiality-preserving way.
no code implementations • 22 Sep 2023 • Daniel Kirste, Niclas Kannengießer, Ricky Lamberty, Ali Sunyaev
The proper design of automated market makers (AMMs) is crucial to enable the continuous trading of assets represented as digital tokens on markets of cryptoeconomic systems.
1 code implementation • 1 May 2023 • Konstantin D. Pandl, Chun-Yin Huang, Ivan Beschastnikh, Xiaoxiao Li, Scott Thiebes, Ali Sunyaev
The valuation of data points through DDVal allows to also draw hierarchical conclusions on the contribution of institutions, and we empirically show that the accuracy of DDVal in estimating institutional contributions is higher than existing Shapley value approximation methods for federated learning.
1 code implementation • 1 May 2022 • Konstantin D. Pandl, Florian Leiser, Scott Thiebes, Ali Sunyaev
Especially bias, defined as a disparity in the model's predictive performance across different subgroups, may cause unfairness against specific subgroups, which is an undesired phenomenon for trustworthy ML models.
no code implementations • 3 Mar 2022 • Niklas Hasebrook, Felix Morsbach, Niclas Kannengießer, Marc Zöller, Jörg Franke, Marius Lindauer, Frank Hutter, Ali Sunyaev
Advanced programmatic hyperparameter optimization (HPO) methods, such as Bayesian optimization, have high sample efficiency in reproducibly finding optimal hyperparameter values of machine learning (ML) models.
1 code implementation • 29 Nov 2021 • Felix Morsbach, Tobias Dehling, Ali Sunyaev
One barrier to more widespread adoption of differentially private neural networks is the entailed accuracy loss.
no code implementations • 29 Jan 2020 • Konstantin D. Pandl, Scott Thiebes, Manuel Schmidt-Kraepelin, Ali Sunyaev
Previous work highlights several potential benefits of the convergence of AI and DLT but only provides a limited theoretical framework to describe upcoming real-world integration cases of both technologies.