arXiv subjects
Publications and source records attributed to Christian Bauckhage.
We show that the objective function of conventional k-means clustering can be expressed as the Frobenius norm of the difference of a data matrix and a low rank approximation of that data matrix. In short, we show that k-means clustering is a matrix factorization problem. These notes are meant as a reference and intended to provide a guided tour towards a result that is often mentioned but seldom made explicit in the literature.
In this note we briefly study the feasibility of community detection in complex networks using peripheral vertices. Our method suggests a novel direction in axiomizing the problem of clustering in graphs and complex networks by looking at the topological role each vertex plays in the community structure, regardless of the attributes. The promising strength of pseudo-peripheral vertices as a lever for analysis of complex networks is also demonstrated on real-world data.
Motivated by the center-surround mechanism in the human visual attention system, we propose to use average contrast maps for the challenge of pedestrian detection in street scenes due to the observation that pedestrians indeed exhibit discriminative contrast texture. Our main contributions are first to design a local, statistical multi-channel descriptorin order to incorporate both color and gradient information. Second, we introduce a multi-direction and multi-scale contrast scheme based on grid-cells in order to integrate expressive local variations. Contributing to the issue of selecting most discriminative features for assessing and classification, we perform extensive comparisons w.r.t. statistical descriptors, contrast measurements, and scale structures. This way, we obtain reasonable results under various configurations. Empirical findings from applying our optimized detector on the INRIA and Caltech pedestrian datasets show that our features yield state-of-the-art performance in pedestrian detection.
Properties of networks are often characterized in terms of features such as node degree distributions, average path lengths, diameters, or clustering coefficients. Here, we study shortest path length distributions. On the one hand, average as well as maximum distances can be determined therefrom; on the other hand, they are closely related to the dynamics of network spreading processes. Because of the combinatorial nature of networks, we apply maximum entropy arguments to derive a general, physically plausible model. In particular, we establish the generalized Gamma distribution as a continuous characterization of shortest path length histograms of networks or arbitrary topology. Experimental evaluations corroborate our theoretical results.
We introduce propagation kernels, a general graph-kernel framework for efficiently measuring the similarity of structured data. Propagation kernels are based on monitoring how information spreads through a set of given graphs. They leverage early-stage distributions from propagation schemes such as random walks to capture structural information encoded in node labels, attributes, and edge information. This has two benefits. First, off-the-shelf propagation schemes can be used to naturally construct kernels for many graph types, including labeled, partially labeled, unlabeled, directed, and attributed graphs. Second, by leveraging existing efficient and informative propagation schemes, propagation kernels can be considerably faster than state-of-the-art approaches without sacrificing predictive performance. We will also show that if the graphs at hand have a regular structure, for instance when modeling image or video data, one can exploit this regularity to scale the kernel computation to large databases of graphs with thousands of nodes. We support our contributions by exhaustive experiments on a number of real-world graphs from a variety of application domains.
We briefly review the basic ideas behind archetypal analysis for matrix factorization and discuss its behavior in approximating the convex hull of a data sample. We then ask how good such approximations can be and consider different cases. Understanding archetypal analysis as the problem of computing a convexity constrained low-rank approximation of the identity matrix provides estimates for archetypal analysis and the SiVM heuristic.
In this note, we show how to marginalize over the damping parameter of the PageRank equation so as to obtain a parameter-free version known as TotalRank. Our discussion is meant as a reference and intended to provide a guided tour towards an interesting result that has applications in information retrieval and classification.
The analysis of user behavior in digital games has been aided by the introduction of user telemetry in game development, which provides unprecedented access to quantitative data on user behavior from the installed game clients of the entire population of players. Player behavior telemetry datasets can be exceptionally complex, with features recorded for a varying population of users over a temporal segment that can reach years in duration. Categorization of behaviors, whether through descriptive methods (e.g. segmention) or unsupervised/supervised learning techniques, is valuable for finding patterns in the behavioral data, and developing profiles that are actionable to game developers. There are numerous methods for unsupervised clustering of user behavior, e.g. k-means/c-means, Non-negative Matrix Factorization, or Principal Component Analysis. Although all yield behavior categorizations, interpretation of the resulting categories in terms of actual play behavior can be difficult if not impossible. In this paper, a range of unsupervised techniques are applied together with Archetypal Analysis to develop behavioral clusters from playtime data of 70,014 World of Warcraft players, covering a five year interval. The techniques are evaluated with respect to their ability to develop actionable behavioral profiles from the dataset.
We analyze general trends and pattern in time series that characterize the dynamics of collective attention to social media services and Web-based businesses. Our study is based on search frequency data available from Google Trends and considers 175 different services. For each service, we collect data from 45 different countries as well as global averages. This way, we obtain more than 8,000 time series which we analyze using diffusion models from the economic sciences. We find that these models accurately characterize the empirical data and our analysis reveals that collective attention to social media grows and subsides in a highly regular and predictable manner. Regularities persist across regions, cultures, and topics and thus hint at general mechanisms that govern the adoption of Web-based services. We discuss several cases in detail to highlight interesting findings. Our methods are of economic interest as they may inform investment decisions and can help assessing at what stage of the general life-cycle a Web service is at.
In this note, we characterize the Gompertz distribution in terms of extreme value distributions and point out that it implicitly models the interplay of two antagonistic growth processes. In addition, we derive a closed form expressions for the Kullback-Leibler divergence between two Gompertz Distributions. Although the latter is rather easy to obtain, it seems not to have been widely reported before.
We derive a closed form solution for the Kullback-Leibler divergence between two generalized gamma distributions. These notes are meant as a reference and provide a guided tour towards a result of practical interest that is rarely explicated in the literature.
We consider the problem of clustering data that reside on discrete, low dimensional lattices. Canonical examples for this setting are found in image segmentation and key point extraction. Our solution is based on a recent approach to information theoretic clustering where clusters result from an iterative procedure that minimizes a divergence measure. We replace costly processing steps in the original algorithm by means of convolutions. These allow for highly efficient implementations and thus significantly reduce runtime. This paper therefore bridges a gap between machine learning and signal processing.
We derive a closed form solution for the Kullback-Leibler divergence between two Weibull distributions. These notes are meant as reference material and intended to provide a guided tour towards a result that is often mentioned but seldom made explicit in the literature.
Many collective human activities have been shown to exhibit universal patterns. However, the possibility of universal patterns across timing events of researcher migration has barely been explored at global scale. Here, we show that timing events of migration within different countries exhibit remarkable similarities. Specifically, we look at the distribution governing the data of researcher migration inferred from the web. Compiling the data in itself represents a significant advance in the field of quantitative analysis of migration patterns. Official and commercial records are often access restricted, incompatible between countries, and especially not registered across researchers. Instead, we introduce GeoDBLP where we propagate geographical seed locations retrieved from the web across the DBLP database of 1,080,958 authors and 1,894,758 papers. But perhaps more important is that we are able to find statistical patterns and create models that explain the migration of researchers. For instance, we show that the science job market can be treated as a Poisson process with individual propensities to migrate following a log-normal distribution over the researcher's career stage. That is, although jobs enter the market constantly, researchers are generally not "memoryless" but have to care greatly about their next move. The propensity to make k>1 migrations, however, follows a gamma distribution suggesting that migration at later career stages is "memoryless". This aligns well but actually goes beyond scientometric models typically postulated based on small case studies. On a very large, transnational scale, we establish the first general regularities that should have major implications on strategies for education and research worldwide.
Understanding the adaptation process of plants to drought stress is essential in improving management practices, breeding strategies as well as engineering viable crops for a sustainable agriculture in the coming decades. Hyper-spectral imaging provides a particularly promising approach to gain such understanding since it allows to discover non-destructively spectral characteristics of plants governed primarily by scattering and absorption characteristics of the leaf internal structure and biochemical constituents. Several drought stress indices have been derived using hyper-spectral imaging. However, they are typically based on few hyper-spectral images only, rely on interpretations of experts, and consider few wavelengths only. In this study, we present the first data-driven approach to discovering spectral drought stress indices, treating it as an unsupervised labeling problem at massive scale. To make use of short range dependencies of spectral wavelengths, we develop an online variational Bayes algorithm for latent Dirichlet allocation with convolved Dirichlet regularizer. This approach scales to massive datasets and, hence, provides a more objective complement to plant physiological practices. The spectral topics found conform to plant physiological knowledge and can be computed in a fraction of the time compared to existing LDA approaches.