Thomas Liebig

Materna SE · Artificial Intelligence Unit

Our study reveals new theoretical insights into over-smoothing and feature over-correlation in deep graph neural networks. We show the prevalence of invariant subspaces, demonstrating a fixed relative behavior that is unaffected by feature transformations. Our work clarifies recent observations related to convergence to a constant state and a poten...

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 nodes making them indistinguishable, over-squashing refers to the inability of GNNs to propagate information over long distances, as exponentially many node states are squash...

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 and leaves models unable to capture long-range relationships. The primary reason for the shallow design results from over-smoothing, which leads node states to become more...

Sustainability is the current global challenge. This is reflected in the demand for healthy food and CO neutrality. These challenges can be met with the industrial cultivation of algae: Algae can be used as food supplements, nutraceuticals, pharmaceuticals, fuel, CO sinks, and obtain high relative yield density per area. Current limitations in thei...

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 spatio-temporal data, we will propose two efficient models which use Differential Privacy and decentralized LSTM-Learning: One, in which a Long Short Term Memory (LSTM) mod...

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 in the training data tend to become support vectors, and are hence considered "normal". In this article, we improve the effectiveness to detect outliers in dirty training...

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 coverage of sensors is generally unavailable and would practically be infeasible due to limitations in budget and other resources during deployment and maintenance. Current...

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 often insufficient to guarantee data privacy since it is often used to train machine learning models, which can expose information about the training data. Thus, a guaran...

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 Consumer Privacy Act. Thus, multiple approaches were presented to remove the influence of specific target data points from a trained model. However, when evaluating the succes...

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 and leaves models unable to capture long-range relationships. The primary reason for the shallow design results from over-smoothing, which leads node states to become more...

While probabilistic graphical models are a central tool for reasoning under uncertainty in AI, they are in general not as expressive as deep neural models, and inference is notoriously hard and slow. In contrast, deep probabilistic models such as sum-product networks (SPNs) capture joint distributions and ensure tractable inference, but still lack...

The development and implementation of artificial intelligence (AI) applications in health care contexts is a concurrent research and management question. Especially for hospitals, the expectations regarding improved efficiency and effectiveness by the introduction of novel AI applications are huge. However, experiences with real-life AI use cases a...

Due to IoT and Industry 4.0, more and more data is collected by sensor nodes, which send their data to a central data lake. This approach results in high data traffic and privacy risk, which we want to address in this paper. Therefore we use an existing Learning from Label Proportions (LLP) algorithm, to use the decentralized properties and extend...

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, we highlight based on a simulation scenario, how sparse observations, as obtained by a mobile application could be utilized to estimate parking lot occupancy. Our simul...

We study the applicability of blockchain technology for distributed event detection under resource constraints. Therefore we provide a test-suite with several promising consensus methods (Proof-of-Work, Proof-of-Stake, Distributed Proof-of-Work, and Practical Proof-of-Kernel-Work). This is the first work analyzing the communication costs of blockch...

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. However, the massive increases in Machine-type Communication (MTC) highly stress the capacities of the network infrastructure. With the system-immanent limitation of resour...

Bayesian networks are a central tool in machine learning and artificial intelligence, and make use of conditional independencies to impose structure on joint distributions. However, they are generally not as expressive as deep learning models and inference is hard and slow. In contrast, deep probabilistic models such as sum-product networks (SPNs)...

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. However, the massive increases in Machine-type Communication (MTC) highly stress the capacities of the network infrastructure. With the system-immanent limitation of resour...

We study the applicability of blockchain technology for distributed event detection under resource constraints. Therefore we provide a test-suite with several promising consensus methods (Proof-of-Work, Proof-of-Stake, Distributed Proof-of-Work, and Practical Proof-of-Kernel-Work). This is the first work analyzing the communication costs of blockch...

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 mechanism based on contextual bandits to provide incentives for distributing charging load and preventing network failure. The presented work combines the microscopic mobility s...

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 period - the hybrid vehicular traffic - is often neglected. However, within the next decades, automotive systems with heterogeneous autonomy levels will share the same road...

The nature of contemporary spatial data infrastructures lies in the provision of geospatial information in an on-demand fashion. Although recent applications identified the need to react to real-time information in a time-critical way, research efforts in the field of geospatial Internet of Things in particular have identified substantial gaps in t...

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 mechanism based on contextual bandits to provide incentives for distributing charging load and preventing network failure. The presented work combines the microscopic mobility s...

The nature of contemporary Spatial Data Infrastructures lies in the provision of geospatial information in an on-demand fashion. Though recent applications identified the need to react to real-time information in a time-critical way. In particular, research efforts in the field of geospatial Internet of Things have identified substantial gaps in th...

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 information for crowdsensing-enabled big data services in a smart city context. Consequently, upcoming 5G communication networks will be confronted with massive increases in Machin...

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 conclusion, public cellular networks will be confronted with massive increases in Machine-Type Communication (MTC) and will require efficient communication schemes to minimize th...

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 Internet of Things (IoT) systems. Cars acting as mobile sensors will become important data sources for cloud-based applications like predictive maintenance and dynamic traffic f...

Autonomous robots need to perceive and represent their environments and act accordingly. Using simultaneous localization and mapping (SLAM) methods, robots can build maps of the environment which are efficient for localization and path planning as long as the environment remains unchanged. However, facility logistics environments are not static bec...

Situation-aware route planning gathers increasing interest. The proliferation of various sensor technologies in smart cities allows the incorporation of real-time data and its predictions in the trip planning process. We present a system for individual multi-modal trip planning that incorporates predictions of future public transport delays in rout...

Urban areas are increasingly subject to congestions. Most navigation systems and algorithms that avoid these congestions consider drivers independently and can, thus, cause novel congestions at unexpected places. Pre-computation of optimal trips (Nash equilibrium) could be a solution to the problem but is due to its static nature of no practical re...

Route planning makes direct use of geographic data and provides beneficial recommendations to the public. In real-world the schedule of transit vehicles is dynamic and delays in the schedules occur. Incorporation of these dynamic schedule changes in multi-modal route computation is difficult and requires a lot of computational resources. Our approa...

In this demo we present INSIGHT, a system that provides traffic event detection in Dublin by exploiting Big Data and Crowdsourcing techniques. Our system is able to process and analyze input from multiple heterogeneous urban data sources.

Since the last decades the availability and granularity of location-based data has been rapidly growing. Besides the proliferation of smartphones and location-based social networks, also crowdsourcing and voluntary geographic data led to highly granular mobility data, maps and street networks. In result, location-aware, smart environments are creat...

Proliferation of pervasive devices capturing sensible data streams, e.g. mobility records, raise concerns on individual privacy. Even if the data is aggregated at a central server, location data may identify a particular person. Thus, the transmitted data must be guarded against re-identification and an un-trusted server. This paper overcomes limit...

Modern traffic management should benefit from the diverse sensors, smart phones, and social networks data that offer the potential of enhanced services. In disaster scenarios, it is no longer guaranteed that a central server and reliable communication is always available. This motivates a distributed computing setting with restricted communication....

Individual multi-modal trip planning is a major task in transportation science. With increasing availability of new means of transportation personal constraints (e.g. elevator phobia or fear of flying) and preferences (e.g. train over bus) gain higher impact. Existing trip planners are mostly based on static time-tables and roadnetwork data. Furthe...

We present a novel approach for event recognition in massive streams of heterogeneous data driven by privacy policies and big data event processing. New technologies in mobile computing combined with sensing infrastructures distributed in a city or country are generating massive, poly-structured spatio-temporal data. With a view on emergencies and...

We give an overview of an intelligent urban traffic management system. Complex events related to congestions are detected from heterogeneous sources involving fixed sensors mounted on intersections and mobile sensors mounted on public transport vehicles. To deal with data veracity, sensor disagreements are resolved by crowdsourcing. To deal with da...

Analysis of people's movements represented by continuous sequences of spatio-temporal data tuples have received lots of attention in recent years. The focus of those studies was mostly GPS data recorded on a constant sample rate. However, the creation of intelligent location-aware models and environments also requires reliable localization in indoo...

We consider a city where induction-based vehicle count sensors are installed at some, but not all street junctions. Each sensor regularly outputs a count and a saturation value. We first use a discrete time Gauss-Markov model based on historical data to predict the evolution of these saturation values, and then a Gaussian Process derived from the s...

Smart route planning gathers increasing interest as cities become crowded and jammed. We present a system for individual trip planning that incorporates future traffic hazards in routing. Future traffic conditions are computed by a Spatio-Temporal Random Field based on a stream of sensor readings. In addition, our approach estimates traffic flow in...

Situation dependent route planning gathers increasing interest as cities become crowded and jammed. We present a system for individual trip planning that incorporates future traffic hazards in routing. Future traffic conditions are computed by a Spatio-Temporal Random Field based on a stream of sensor readings. In addition, our approach estimates t...

With the emergence of the mobile app ecosystem, user location data has escaped the grip of the tightly regulated telecommunication industry and is now being collected at unprecedented scale and accuracy by mobile advertising, platform, and app providers. This position paper is based on discussions of the authors at the Dagstuhl seminar on Mobility...

Understanding the spatial and temporal aspects of activities in urban regions is one of the key challenges for the emerging fields of urban computing and emergency management as it provides indispensable insights on the quality of services in urban environments and helps to describe the socio-dynamics of urban districts. This work presents a novel...

Pedestrian quantity estimation receives increasing attention and has important applications, e.g. in location evaluation and risk analysis. In this work, we focus on pedestrian quantity estimation for event monitoring. We address the problem (1) how to estimate quantities for unmeasured locations, and (2) where to place a bounded number of sensors...

In street-based mobility mining, traffic volume estimation receives increasing attention as it provides important applications such as emergency support systems, quality-of-service evaluation and billboard placement. In many real world scenarios, empirical measurements are usually sparse due to some constraints. On the other hand, pedestrians gener...

Continuing advances in modern data acquisition techniques result in rapidly growing amounts of geo-referenced data about moving objects and in emergence of new data types. We define episodic movement data as a new complex data type to be considered in the research fields relevant to data analysis. In episodic movement data, position measurements ma...

Recently evolved Bluetooth tracking technology is currently applied to extract individual pathways, movement patterns or to rank popularity of locations by their visitor quantities. To utilize this technology for the creation of location aware intelligent environments, the next steps are to come up with microscopic traffic values. This work propose...

Emergence of Bluetooth tracking technology for event monitoring is currently applied to extract individual pathways, movement patterns or to rank popularity of locations by their visitor quantities. The next steps are to achieve short term movement predictions, to understand people's motivations and to come up with microscopic traffic values. This...

In recent times, consumer research at major social events received significant interest by organizing companies. Understanding the movements and motivations of the customers enables new business strategies and is needed to minimize the risk of investment. The spatiotemporal complexity of major events poses high demands on survey and analytical meth...

During the past years the first tools for visual analysis of trajectory data appeared. Considering the growing sizes of trajectory collections, one important task is to ensure user interactivity during data analysis. In this paper we present a fast, model-based visualization approach for the analysis of location dependencies in large trajectory col...

Traffic routes through a street network contain patterns and are no random walks. Such patterns exist for instance along streets or between neighbouring street segments. The extraction of these patterns is a challenging task due to the enormous size of city street networks, the large number of required training data and the unknown distribution of...