1 code implementation • NAACL (ACL) 2022 • Eileen Salhofer, Xing Lan Liu, Roman Kern
(2) which examples to annotate?
no code implementations • LREC 2022 • Michael Jantscher, Roman Kern
Understanding the needs and fears of citizens, especially during a pandemic such as COVID-19, is essential for any government or legislative entity.
no code implementations • 5 Feb 2024 • Meng Cao, Hussain Hussain, Sandipan Sikdar, Denis Helic, Markus Strohmaier, Roman Kern
We further study how interventions on network properties influence fairness by examining counterfactual scenarios with alternative evolution outcomes and differing network properties.
no code implementations • 15 Jan 2024 • David Fleischhacker, Wolfgang Goederle, Roman Kern
The model was then fine-tuned with a smaller set of manually annotated historical source data.
no code implementations • 28 Sep 2023 • Lea Demelius, Roman Kern, Andreas Trügler
Differential Privacy has become a widely popular method for data protection in machine learning, especially since it allows formulating strict mathematical privacy guarantees.
no code implementations • 22 Feb 2023 • Maximilian B. Toller, Bernhard C. Geiger, Roman Kern
Rate-distortion theory-based outlier detection builds upon the rationale that a good data compression will encode outliers with unique symbols.
1 code implementation • 13 Sep 2022 • Hussain Hussain, Meng Cao, Sandipan Sikdar, Denis Helic, Elisabeth Lex, Markus Strohmaier, Roman Kern
We hope our findings raise awareness about this issue in our community and lay a foundation for the future development of GNN models that are more robust to such attacks.
no code implementations • 20 May 2022 • Samuel Sousa, Roman Kern
Deep learning (DL) models for natural language processing (NLP) tasks often handle private data, demanding protection against breaches and disclosures.
no code implementations • 20 Oct 2021 • Samuel Sousa, Christian Guetl, Roman Kern
Privacy is of worldwide concern regarding activities and processes that include sensitive data.
no code implementations • 18 Oct 2021 • Patrick Ofner, Roman Kern
We show that both approaches can improve the generalization capability of a particular type of MANN, the differentiable neural computer (DNC), and compare our approaches to a stateful and a stateless controller on a set of algorithmic tasks.
1 code implementation • 23 Jul 2021 • Hussain Hussain, Tomislav Duricic, Elisabeth Lex, Denis Helic, Markus Strohmaier, Roman Kern
In this work, we study adversarial attacks that are uninformed, where an attacker only has access to the graph structure, but no information about node attributes.
no code implementations • 22 Apr 2021 • Adrian Remonda, Sarah Krebs, Eduardo Veas, Granit Luzhnica, Roman Kern
This paper explores the use of reinforcement learning (RL) models for autonomous racing.
no code implementations • 24 Mar 2021 • Stefan Schrunner, Michael Scheiber, Anna Jenul, Anja Zernig, Andre Kästner, Roman Kern
Since high data volume and complex data formats delivered in modern high-end production environments go beyond the scope of classical process control systems, more advanced tools involving machine learning are required to reliably recognize failure patterns.
no code implementations • 16 Nov 2020 • Jan Egger, Antonio Pepe, Christina Gsaxner, Yuan Jin, Jianning Li, Roman Kern
These networks outperform the state-of-the-art methods in different tasks and, because of this, the whole field saw an exponential growth during the last years.
1 code implementation • 30 Oct 2020 • Hussain Hussain, Tomislav Duricic, Elisabeth Lex, Roman Kern, Denis Helic
In this work, we systematically study the impact of community structure on the performance of GNNs in semi-supervised node classification on graphs.
no code implementations • 29 Oct 2020 • Nikolaos Nikolaou, Ingo P. Waldmann, Angelos Tsiaras, Mario Morvan, Billy Edwards, Kai Hou Yip, Giovanna Tinetti, Subhajit Sarkar, James M. Dawson, Vadim Borisov, Gjergji Kasneci, Matej Petkovic, Tomaz Stepisnik, Tarek Al-Ubaidi, Rachel Louise Bailey, Michael Granitzer, Sahib Julka, Roman Kern, Patrick Ofner, Stefan Wagner, Lukas Heppe, Mirko Bunse, Katharina Morik
For instance, the most prolific method for detecting exoplanets and inferring several of their characteristics, transit photometry, is very sensitive to the presence of stellar spots.
no code implementations • 18 Aug 2020 • Maximilian Toller, Bernhard C. Geiger, Roman Kern
Distance-based classification is among the most competitive classification methods for time series data.
1 code implementation • 14 Nov 2019 • Maximilian Toller, Roman Kern
Many of the methods for identifying periodic patterns require time series' season length as input parameter.
no code implementations • 12 Aug 2019 • Dominik Kowald, Matthias Traub, Dieter Theiler, Heimo Gursch, Emanuel Lacic, Stefanie Lindstaedt, Roman Kern, Elisabeth Lex
The presented work contributes to the tripartite recommendation problem in general and to the under-researched portfolio of evaluating recommender systems for data markets in particular.
no code implementations • SEMEVAL 2019 • Kevin Winter, Roman Kern
This paper presents the Know-Center system submitted for task 5 of the SemEval-2019 workshop.
no code implementations • SEMEVAL 2017 • Roman Kern, Stefan Falk, Andi Rexha
We competed in Subtask 1 and 2 which consist respectively in identifying all the key phrases in scientific publications and label them with one of the three categories: Task, Process, and Material.