61 citations
- Universität KoblenzDE20 papers
- University of BonnDE5 papers
- Chemnitz University of TechnologyDE4 papers
- GESIS - Leibniz Institute for the Social SciencesDE4 papers
- Fraunhofer Institute for Applied Information TechnologyDE2 papers
- Graz University of TechnologyAT2 papers
- Hanoi University of Science and TechnologyVN2 papers
- RWTH Aachen UniversityDE2 papers
- Technical University of MunichDE2 papers
- Technische Universität IlmenauDE2 papers
- University of Koblenz and LandauDE2 papers
- University of RostockDE2 papers
7 papers · 1 filter
Product units in gated recurrent units improve nuclear-mass prediction
Ziyuan Li, Paulo S. A. Freitas, John W. Clark +1
The prediction of masses of atomic nuclei using machine learning can complement theoretical models and advance the exploration of poorly known domains of the nuclear chart. We prop…
Modeling Nonlinear Feature Interactions with Product-Unit Residual Networks
Ziyuan Li, Uwe Jaekel, Babette Dellen
Understanding nonlinear feature interactions is crucial in science and engineering, yet standard multilayer perceptrons (MLPs) often capture such interactions only implicitly, lead…
FairFinGAN: Fairness-aware Synthetic Financial Data Generation
Tai Le Quy, Dung Nguyen Tuan, Trung Nguyen Thanh +3
Financial datasets often suffer from bias that can lead to unfair decision-making in automated systems. In this work, we propose FairFinGAN, a WGAN-based framework designed to gene…
A Deep Latent Factor Graph Clustering with Fairness-Utility Trade-off Perspective
Siamak Ghodsi, Amjad Seyedi, Tai Le Quy +2
Fair graph clustering seeks partitions that respect network structure while maintaining proportional representation across sensitive groups, with applications spanning community de…
FACROC: a fairness measure for FAir Clustering through ROC curves
Tai Le Quy, Long Le Thanh, Lan Luong Thi Hong +1
Fair clustering has attracted remarkable attention from the research community. Many fairness measures for clustering have been proposed; however, they do not take into account the…
Backdoor attacks on DNN and GBDT -- A Case Study from the insurance domain
Robin Kühlem, Daniel Otten, Daniel Ludwig +3
Machine learning (ML) will likely play a large role in many processes in the future, also for insurance companies. However, ML models are at risk of being attacked and manipulated.…