Search

In 2017 Day et al. introduced the notion of locality as a structural complexity-measure for patterns in the field of pattern matching established by Angluin in 1980. In 2019 Casel et al. showed that determining the locality of an arbitrary pattern is NP-complete. Inspired by hierarchical clustering, we extend the notion to coloured graphs, i.e., given a coloured graph determine an enumeration of the colours such that colouring the graph stepwise according to the enumeration leads to as few clusters as possible. Next to first theoretical results on graph classes, we propose a priority search algorithm to compute the $k$-locality of a graph. The algorithm is optimal in the number of marking prefix expansions, and is faster by orders of magnitude than an exhaustive search. Finally, we perform a case study on a DBLP subgraph to demonstrate the potential of $k$-locality for knowledge discovery.

Mobility data captures the locations of moving objects such as humans, animals, and cars. With the availability of GPS-equipped mobile devices and other inexpensive location-tracking technologies, mobility data is collected ubiquitously. In recent years, the use of mobility data has demonstrated significant impact in various domains including traffic management, urban planning, and health sciences. In this paper, we present the emerging domain of mobility data science. Towards a unified approach to mobility data science, we envision a pipeline having the following components: mobility data collection, cleaning, analysis, management, and privacy. For each of these components, we explain how mobility data science differs from general data science, we survey the current state of the art and describe open challenges for the research community in the coming years., Comment: Updated to reflect the major revision for ACM Transactions on Spatial Algorithms and Systems (TSAS). This version reflects the final version accepted by ACM TSAS

Group Anomaly Detection (GAD) identifies unusual pattern in groups where individual members might not be anomalous. This task is of major importance across multiple disciplines, in which also sequences like trajectories can be considered as a group. As groups become more diverse in heterogeneity and size, detecting group anomalies becomes challenging, especially without supervision. Though Recurrent Neural Networks are well established deep sequence models, their performance can decrease with increasing sequence lengths. Hence, this paper introduces GADformer, a BERT-based model for attention-driven GAD on trajectories in unsupervised and semi-supervised settings. We demonstrate how group anomalies can be detected by attention-based GAD. We also introduce the Block-Attention-anomaly-Score (BAS) to enhance model transparency by scoring attention patterns. In addition to that, synthetic trajectory generation allows various ablation studies. In extensive experiments we investigate our approach versus related works in their robustness for trajectory noise and novelties on synthetic data and three real world datasets., Comment: accepted at International Joint Conference on Neural Networks (IJCNN) 2024, Yokohama, Japan

Layer-wise relevance propagation (LRP) is a widely used and powerful technique to reveal insights into various artificial neural network (ANN) architectures. LRP is often used in the context of image classification. The aim is to understand, which parts of the input sample have highest relevance and hence most influence on the model prediction. Relevance can be traced back through the network to attribute a certain score to each input pixel. Relevance scores are then combined and displayed as heat maps and give humans an intuitive visual understanding of classification models. Opening the black box to understand the classification engine in great detail is essential for domain experts to gain trust in ANN models. However, there are pitfalls in terms of model-inherent artifacts included in the obtained relevance maps, that can easily be missed. But for a valid interpretation, these artifacts must not be ignored. Here, we apply and revise LRP on various ANN architectures trained as classifiers on geospatial and synthetic data. Depending on the network architecture, we show techniques to control model focus and give guidance to improve the quality of obtained relevance maps to separate facts from artifacts., Comment: Fixed typo

Artificial neural networks (ANNs) are known to be powerful methods for many hard problems (e.g. image classification, speech recognition or time series prediction). However, these models tend to produce black-box results and are often difficult to interpret. Layer-wise relevance propagation (LRP) is a widely used technique to understand how ANN models come to their conclusion and to understand what a model has learned. Here, we focus on Echo State Networks (ESNs) as a certain type of recurrent neural networks, also known as reservoir computing. ESNs are easy to train and only require a small number of trainable parameters, but are still black-box models. We show how LRP can be applied to ESNs in order to open the black-box. We also show how ESNs can be used not only for time series prediction but also for image classification: Our ESN model serves as a detector for El Nino Southern Oscillation (ENSO) from sea surface temperature anomalies. ENSO is actually a well-known problem and has been extensively discussed before. But here we use this simple problem to demonstrate how LRP can significantly enhance the explainablility of ESNs., Comment: Shortened title, corrected author affiliation, added citation reference: Accepted at 3rd International Conference on Machine Learning Techniques (MLTEC 2022), Zurich, Switzerland

We discuss topological aspects of cluster analysis and show that inferring the topological structure of a dataset before clustering it can considerably enhance cluster detection: theoretical arguments and empirical evidence show that clustering embedding vectors, representing the structure of a data manifold instead of the observed feature vectors themselves, is highly beneficial. To demonstrate, we combine manifold learning method UMAP for inferring the topological structure with density-based clustering method DBSCAN. Synthetic and real data results show that this both simplifies and improves clustering in a diverse set of low- and high-dimensional problems including clusters of varying density and/or entangled shapes. Our approach simplifies clustering because topological pre-processing consistently reduces parameter sensitivity of DBSCAN. Clustering the resulting embeddings with DBSCAN can then even outperform complex methods such as SPECTACL and ClusterGAN. Finally, our investigation suggests that the crucial issue in clustering does not appear to be the nominal dimension of the data or how many irrelevant features it contains, but rather how \textit{separable} the clusters are in the ambient observation space they are embedded in, which is usually the (high-dimensional) Euclidean space defined by the features of the data. Our approach is successful because we perform the cluster analysis after projecting the data into a more suitable space that is optimized for separability, in some sense., Comment: 43, pages, 10 figures

Smart factories are equipped with machines that can sense their manufacturing environments, interact with each other, and control production processes. Smooth operation of such factories requires that the machines and engineering personnel that conduct their monitoring and diagnostics share a detailed common industrial knowledge about the factory, e.g., in the form of knowledge graphs. Creation and maintenance of such knowledge is expensive and requires automation. In this work we show how machine learning that is specifically tailored towards industrial applications can help in knowledge graph completion. In particular, we show how knowledge completion can benefit from event logs that are common in smart factories. We evaluate this on the knowledge graph from a real world-inspired smart factory with encouraging results.

The reverse k-nearest neighbor (RkNN) query is an established query type with various applications reaching from identifying highly influential objects over incrementally updating kNN graphs to optimizing sensor communication and outlier detection. State-of-the-art solutions exploit that the k-distances in real-world datasets often follow the power-law distribution, and bound them with linear lines in log-log space. In this work, we investigate this assumption and uncover that it is violated in regions of changing density, which we show are typical for real-life datasets. Towards a generic solution, we pose the estimation of k-distances as a regression problem. Thereby, we enable harnessing the power of the abundance of available Machine Learning models and profiting from their advancement. We propose a flexible approach which allows steering the performance-memory consumption trade-off, and in particular to find good solutions with a fixed memory budget crucial in the context of edge computing. Moreover, we show how to obtain and improve guaranteed bounds essential to exact query processing. In experiments on real-world datasets, we demonstrate how this framework can significantly reduce the index memory consumption, and strongly reduce the candidate set size. We publish our code at https://github.com/sobermeier/nonlinear-kdist.

Rectangles are used to approximate objects, or sets of objects, in a plethora of applications, systems and index structures. Many tasks, such as nearest neighbor search and similarity ranking, require to decide if objects in one rectangle A may, must, or must not be closer to objects in a second rectangle B, than objects in a third rectangle R. To decide this relation of "Spatial Domination" it can be shown that using minimum and maximum distances it is often impossible to detect spatial domination. This spatial gem provides a necessary and sufficient decision criterion for spatial domination that can be computed efficiently even in higher dimensional space. In addition, this spatial gem provides an example, pseudocode and an implementation in Python.

To increase the computational efficiency of interest-point based object retrieval, researchers have put remarkable research efforts into improving the efficiency of kNN-based feature matching, pursuing to match thousands of features against a database within fractions of a second. However, due to the high-dimensional nature of image features that reduces the effectivity of index structures (curse of dimensionality), due to the vast amount of features stored in image databases (images are often represented by up to several thousand features), this ultimate goal demanded to trade query runtimes for query precision. In this paper we address an approach complementary to indexing in order to improve the runtimes of retrieval by querying only the most promising keypoint descriptors, as this affects matching runtimes linearly and can therefore lead to increased efficiency. As this reduction of kNN queries reduces the number of tentative correspondences, a loss of query precision is minimized by an additional image-level correspondence generation stage with a computational performance independent of the underlying indexing structure. We evaluate such an adaption of the standard recognition pipeline on a variety of datasets using both SIFT and state-of-the-art binary descriptors. Our results suggest that decreasing the number of queried descriptors does not necessarily imply a reduction in the result quality as long as alternative ways of increasing query recall (by thoroughly selecting k) and MAP (using image-level correspondence generation) are considered.