27 citations
- ETH ZurichCH2 papers
- University of Applied Sciences of the GrisonsCH2 papers
- Warsaw University of TechnologyPL2 papers
- Centre for Mental HealthGB1 paper
- Digital Catapult (United Kingdom)GB1 paper
- Exponent (United States)US1 paper
- GESIS - Leibniz Institute for the Social SciencesDE1 paper
- Graz University of TechnologyAT1 paper
- HSBC HoldingsGB1 paper
- Know Center Research GmbH (Austria)AT1 paper
- L3S Research CenterDE1 paper
- Max Planck InnovationDE1 paper
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2022★ 17 cited
Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural Networks
Hussain Hussain, Meng Cao, Sandipan Sikdar +4
We present evidence for the existence and effectiveness of adversarial attacks on graph neural networks (GNNs) that aim to degrade fairness. These attacks can disadvantage a partic…
cs.LG2021★ 27 cited
Laplace Redux -- Effortless Bayesian Deep Learning
Erik Daxberger, Agustinus Kristiadi, Alexander Immer +3
Bayesian formulations of deep learning have been shown to have compelling theoretical properties and offer practical functional benefits, such as improved predictive uncertainty qu…