no code implementations • 17 Apr 2019 • Julian Stier, Gabriele Gianini, Michael Granitzer, Konstantin Ziegler
In previous work, heuristics based on using the weight distribution of a neuron as contribution measure have shown some success, but do not provide a proper theoretical understanding.
Ranked #1 on Network Pruning on MNIST
1 code implementation • 15 May 2019 • Yvan Lucas, Pierre-Edouard Portier, Léa Laporte, Olivier Caelen, Liyun He-Guelton, Sylvie Calabretto, Michael Granitzer
In this article, we model a sequence of credit card transactions from three different perspectives, namely (i) does the sequence contain a Fraud?
no code implementations • SEMEVAL 2019 • Jelena Mitrovi{\'c}, Bastian Birkeneder, Michael Granitzer
In addition, we evaluate our approach on a different dataset and show that our model is capable of detecting online aggressiveness in both English and German tweets.
no code implementations • 17 Jun 2019 • Yvan Lucas, Pierre-Edouard Portier, Léa Laporte, Sylvie Calabretto, Liyun He-Guelton, Frederic Oblé, Michael Granitzer
This phenomenon is named dataset shift or concept drift in the domain of fraud detection.
1 code implementation • 3 Sep 2019 • Yvan Lucas, Pierre-Edouard Portier, Léa Laporte, Liyun He-Guelton, Olivier Caelen, Michael Granitzer, Sylvie Calabretto
Our multiple perspectives HMM-based approach offers automated feature engineering to model temporal correlations so as to improve the effectiveness of the classification task and allows for an increase in the detection of fraudulent transactions when combined with the state of the art expert based feature engineering strategy for credit card fraud detection.
no code implementations • 16 Oct 2019 • Julian Stier, Michael Granitzer
Sparse Neural Networks regained attention due to their potential for mathematical and computational advantages.
Ranked #1 on Neural Architecture Search on MNIST
2 code implementations • 20 Oct 2019 • Van Bach Nguyen, Belaid Mohamed Karim, Bao Long Vu, Jörg Schlötterer, Michael Granitzer
In this report, we introduce the progress to learn the policy for Malaria Control as a Reinforcement Learning problem in the KDD Cup Challenge 2019 and propose diverse solutions to deal with the limited observations problem.
no code implementations • 9 Dec 2019 • Christian Reiser, Jörg Schlötterer, Michael Granitzer
We consider the initial situation where a dataset has been over-partitioned into $k$ clusters and seek a domain independent way to merge those initial clusters.
1 code implementation • 27 Dec 2019 • Amirhossein Ansari, Masoud Dadgar, Ali Hamzeh, Jörg Schlötterer, Michael Granitzer
In this work, we integrate these two lines of research and propose a new scenario where competition happens in two phases.
Social and Information Networks Computer Science and Game Theory
1 code implementation • 12 Feb 2020 • Fatemeh Salehi Rizi, Joerg Schloetterer, Michael Granitzer
Computing shortest path distances between nodes lies at the heart of many graph algorithms and applications.
no code implementations • 16 Feb 2020 • Fatemeh Salehi Rizi, Michael Granitzer, Konstantin Ziegler
This social network can be efficiently analyzed after learning representations of the ego and its alters in a low-dimensional, real vector space.
no code implementations • 16 Feb 2020 • Fatemeh Salehi Rizi, Michael Granitzer
In this paper, we propose to model the social influence of friends on event attendance.
no code implementations • 17 Feb 2020 • Joerg Schloetterer, Martin Wehking, Fatemeh Salehi Rizi, Michael Granitzer
Graph embedding has recently gained momentum in the research community, in particular after the introduction of random walk and neural network based approaches.
no code implementations • LREC 2020 • Cristina Arhiliuc, Jelena Mitrovi{\'c}, Michael Granitzer
The Common European Framework of Reference (CEFR) provides generic guidelines for the evaluation of language proficiency.
no code implementations • LREC 2020 • Tommaso Caselli, Valerio Basile, Jelena Mitrovi{\'c}, Inga Kartoziya, Michael Granitzer
However, there is a lack of data sets that take into account the degree of explicitness.
1 code implementation • 7 Jun 2020 • Julian Stier, Michael Granitzer
Learning distributions of graphs can be used for automatic drug discovery, molecular design, complex network analysis, and much more.
Ranked #1 on Graph Embedding on Barabasi-Albert
no code implementations • 14 Jul 2020 • Mathieu Garchery, Michael Granitzer
We evaluate ADSAGE on authentication, email traffic and web browsing logs from the CERT insider threat datasets, as well as on real-world authentication events.
1 code implementation • ACL (WOAH) 2021 • Tommaso Caselli, Valerio Basile, Jelena Mitrović, Michael Granitzer
In this paper, we introduce HateBERT, a re-trained BERT model for abusive language detection in English.
Ranked #1 on Hate Speech Detection on AbusEval
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 • SEMEVAL 2020 • Omar Hussein, Hachem Sfar, Jelena Mitrovi{\'c}, Michael Granitzer
This paper describes a neural network (NN) model that was used for participating in the OffensEval, Task 12 of the SemEval 2020 workshop.
no code implementations • SEMEVAL 2020 • Davide Colla, Tommaso Caselli, Valerio Basile, Jelena Mitrovi{\'c}, Michael Granitzer
We introduce an approach to multilingual Offensive Language Detection based on the mBERT transformer model.
no code implementations • SEMEVAL 2020 • Ehab Hamdy, Jelena Mitrovi{\'c}, Michael Granitzer
In this paper, we introduce our submission for the SemEval Task 12, sub-tasks A and B for offensive language identification and categorization in English tweets.
1 code implementation • 21 Mar 2021 • Sahib Julka, Vishal Sowrirajan, Joerg Schloetterer, Michael Granitzer
During prediction, CSG forecasts future speed from latent space and conditions its generation based on it.
1 code implementation • 27 Jul 2021 • Julian Stier, Harshil Darji, Michael Granitzer
Sparsity in the structure of Neural Networks can lead to less energy consumption, less memory usage, faster computation times on convenient hardware, and automated machine learning.
1 code implementation • 12 Nov 2021 • Julian Stier, Michael Granitzer
deepstruct connects deep learning models and graph theory such that different graph structures can be imposed on neural networks or graph structures can be extracted from trained neural network models.
no code implementations • 11 Apr 2022 • Van Bach Nguyen, Kanishka Ghosh Dastidar, Michael Granitzer, Wissam Siblini
We believe that future works on this new paradigm will have a significant impact on the detection of compromised cards.
1 code implementation • 12 Sep 2022 • Christofer Fellicious, Stewart Sentanoe, Michael Granitzer, Hans P. Reiser
A commonly used method in digital forensics is to extract data from the main memory of a digital device.
no code implementations • 7 Mar 2023 • Harshil Darji, Jelena Mitrović, Michael Granitzer
Even though there is much research done on NER using BERT and other popular language models, the same is not explored in detail when it comes to Legal NLP or Legal Tech.
1 code implementation • 26 Apr 2023 • Mehdi Ben Amor, Michael Granitzer, Jelena Mitrović
Therefore, we conduct an in-depth evaluation of the impact of position bias on the performance of LMs when fine-tuned on token classification benchmarks.
no code implementations • 12 May 2023 • Sahib Julka, Michael Granitzer
Planetary science research involves analysing vast amounts of remote sensing data, which are often costly and time-consuming to annotate and process.
1 code implementation • 13 Jul 2023 • Ousmane Touat, Julian Stier, Pierre-Edouard Portier, Michael Granitzer
We use these metrics to compare GraphRNN and GRAN, two well-known generative models for graphs, and unveil the influence of node orderings.
no code implementations • 3 Aug 2023 • Veronika Hackl, Alexandra Elena Müller, Michael Granitzer, Maximilian Sailer
Statistical analysis was conducted in order to learn more about the interrater reliability, consistency of the ratings across iterations and the correlation between ratings in terms of content and style.
1 code implementation • 5 Dec 2023 • Max Klabunde, Mehdi Ben Amor, Michael Granitzer, Florian Lemmerich
Understanding the similarity of the numerous released large language models (LLMs) has many uses, e. g., simplifying model selection, detecting illegal model reuse, and advancing our understanding of what makes LLMs perform well.
no code implementations • 2 Apr 2024 • Nataliia Kholodna, Sahib Julka, Mohammad Khodadadi, Muhammed Nurullah Gumus, Michael Granitzer
To address this gap, we propose leveraging the potential of LLMs in the active learning loop for data annotation.
no code implementations • 2 Apr 2024 • Michael Dinzinger, Florian Heß, Michael Granitzer
The groundbreaking advancements around generative AI have recently caused a wave of concern culminating in a row of lawsuits, including high-profile actions against Stability AI and OpenAI.
1 code implementation • LREC 2022 • Ramona Kühn, Jelena Mitrović, Michael Granitzer
GRhOOT, the German RhetOrical OnTology, is a domain ontology of 110 rhetorical figures in the German language.