52 citations · 152 across the 17 of their papers we have counts for
17 papers
Curvature-based Pooling within Graph Neural Networks
Cedric Sanders, Andreas Roth, Thomas Liebig
Over-squashing and over-smoothing are two critical issues, that limit the capabilities of graph neural networks (GNNs). While over-smoothing eliminates the differences between node…
Rank Collapse Causes Over-Smoothing and Over-Correlation in Graph Neural Networks
Andreas Roth, Thomas Liebig
Our study reveals new theoretical insights into over-smoothing and feature over-correlation in graph neural networks. Specifically, we demonstrate that with increased depth, node r…
Distributed LSTM-Learning from Differentially Private Label Proportions
Timon Sachweh, Daniel Boiar, Thomas Liebig
Data privacy and decentralised data collection has become more and more popular in recent years. In order to solve issues with privacy, communication bandwidth and learning from sp…
LOSDD: Leave-Out Support Vector Data Description for Outlier Detection
Daniel Boiar, Thomas Liebig, Erich Schubert
Support Vector Machines have been successfully used for one-class classification (OCSVM, SVDD) when trained on clean data, but they work much worse on dirty data: outliers present…
Forecasting Unobserved Node States with spatio-temporal Graph Neural Networks
Andreas Roth, Thomas Liebig
Forecasting future states of sensors is key to solving tasks like weather prediction, route planning, and many others when dealing with networks of sensors. But complete spatial co…
Certified Data Removal in Sum-Product Networks
Alexander Becker, Thomas Liebig
Data protection regulations like the GDPR or the California Consumer Privacy Act give users more control over the data that is collected about them. Deleting the collected data is…
Evaluating Machine Unlearning via Epistemic Uncertainty
Alexander Becker, Thomas Liebig
There has been a growing interest in Machine Unlearning recently, primarily due to legal requirements such as the General Data Protection Regulation (GDPR) and the California Consu…
Transforming PageRank into an Infinite-Depth Graph Neural Network
Andreas Roth, Thomas Liebig
Popular graph neural networks are shallow models, despite the success of very deep architectures in other application domains of deep learning. This reduces the modeling capacity a…
Towards Truck Parking Lot Occupancy Estimation
Florian Ziegler, Maurice Freund, Andreas Rydzek +1
Occupied truck parking lots regularly cause hazardous situations. Estimation of current parking lot state could be utilized to provide drivers parking recommendations. In this work…
Conditional Sum-Product Networks: Imposing Structure on Deep Probabilistic Architectures
Xiaoting Shao, Alejandro Molina, Antonio Vergari +4
Probabilistic graphical models are a central tool in AI; however, they are generally not as expressive as deep neural models, and inference is notoriously hard and slow. In contras…
Charging control of electric vehicles using contextual bandits considering the electrical distribution grid
Christian Römer, Johannes Hiry, Chris Kittl +2
With the proliferation of electric vehicles, the electrical distribution grids are more prone to overloads. In this paper, we study an intelligent pricing and power control mechani…
Boosting Vehicle-to-cloud Communication by Machine Learning-enabled Context Prediction
Benjamin Sliwa, Robert Falkenberg, Thomas Liebig +2
The exploitation of vehicles as mobile sensors acts as a catalyst for novel crowdsensing-based applications such as intelligent traffic control and distributed weather forecast. Ho…
Knowledge Discovery on Blockchains: Challenges and Opportunities
Cedric Sanders, Thomas Liebig
We study the applicability of blockchain technology for distributed event detection under resource constraints. Therefore we provide a test-suite with several promising consensus m…
System-of-Systems Modeling, Analysis and Optimization of Hybrid Vehicular Traffic
Benjamin Sliwa, Thomas Liebig, Tim Vranken +2
While the development of fully autonomous vehicles is one of the major research fields in the Intelligent Transportation Systems (ITSs) domain, the upcoming longterm transition per…
Machine learning based context-predictive car-to-cloud communication using multi-layer connectivity maps for upcoming 5G networks
Benjamin Sliwa, Thomas Liebig, Robert Falkenberg +2
While cars were only considered as means of personal transportation for a long time, they are currently transcending to mobile sensor nodes that gather highly up-to-date informatio…
Resource-efficient Transmission of Vehicular Sensor Data Using Context-aware Communication
Benjamin Sliwa, Thomas Liebig, Robert Falkenberg +2
Upcoming Intelligent Traffic Control Systems (ITSCs) will base their optimization processes on crowdsensing data obtained for cars that are used as mobile sensor nodes. In conclusi…
Efficient Machine-type Communication using Multi-metric Context-awareness for Cars used as Mobile Sensors in Upcoming 5G Networks
Benjamin Sliwa, Thomas Liebig, Robert Falkenberg +2
Upcoming 5G-based communication networks will be confronted with huge increases in the amount of transmitted sensor data related to massive deployments of static and mobile Interne…