200 citations
- Graz University of TechnologyAT52 papers
- Johannes Kepler University of LinzAT9 papers
- University of GrazAT7 papers
- Technical University of MunichDE4 papers
- Washington University in St. LouisUS4 papers
- GESIS - Leibniz Institute for the Social SciencesDE3 papers
- Pontificia Universidad Católica de ChileCL3 papers
- Tallinn UniversityEE3 papers
- Austrian Academy of SciencesAT2 papers
- Central Institution for Meteorology and GeodynamicsAT2 papers
- Institute of Electrical and Electronics EngineersUS2 papers
- Institut für InformationsverarbeitungDE2 papers
8 papers · 1 filter
Trustworthy Representation Learning via Information Funnels and Bottlenecks
João Machado de Freitas, Bernhard C. Geiger
Ensuring trustworthiness in machine learning -- by balancing utility, fairness, and privacy -- remains a critical challenge, particularly in representation learning. In this work,…
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…
Modelling the long-term fairness dynamics of data-driven targeted help on job seekers
Sebastian Scher, Simone Kopeinik, Andreas Trügler +1
The use of data-driven decision support by public agencies is becoming more widespread and already influences the allocation of public resources. This raises ethical concerns, as i…
Fast generation of simple directed social network graphs with reciprocal edges and high clustering
Christoph Schweimer
Online social networks have emerged as useful tools to communicate or share information and news on a daily basis. One of the most popular networks is Twitter, where users connect…
Compressed Hierarchical Representations for Multi-Task Learning and Task Clustering
João Machado de Freitas, Sebastian Berg, Bernhard C. Geiger +1
In this paper, we frame homogeneous-feature multi-task learning (MTL) as a hierarchical representation learning problem, with one task-agnostic and multiple task-specific latent re…
Generating Simple Directed Social Network Graphs for Information Spreading
Christoph Schweimer, Christine Gfrerer, Florian Lugstein +4
Online social networks are a dominant medium in everyday life to stay in contact with friends and to share information. In Twitter, users can connect with other users by following…