Christian Bauckhage

Age Recognition in the Wild

In this paper, we present a novel approach to age recognition from facial images. The method we propose, combines several established features in order to characterize facial characteristics and aging patterns. Since we explicitly consider age recognition in the wild, i.e. vast amounts of unconstrained Internet images, the methods we employ are tailored towards speed and efficiency. For evaluation, we test different classifiers on common benchmark data and a new data set of unconstrained images harvested from the Internet. Extensive experimental evaluation shows state of the art performance on the benchmarks, very high accuracy for the novel data set, and superior runtime performance; to our knowledge, this is the first time that automatic age recognition is carried out on a large Internet data set.

Predicting Emerging Trends in Citation Networks

The work presented in this thesis aims to detect emerging trends in citation networks, specifically in US Patent Citation Network, using representational learning methods for graphs. The network of patent citations is an evolving graph, which contains valuable information about innovation and technological change. We investigated the properties of citation networks in order to find suitable random walk sampling strategies for generating accurate embeddings of patents. We demonstrate that our temporal analysis of learned embeddings can detect shifts of patents and reveal emerging technology categories even before the official authorities identify them.

Third Party Effect: Community Based Spreading in Complex Networks

Ein wesentlicher Teil der Netzwerkforschung wurde dem Studium von Streuprozessen und Gemeinschaftserkennung gewidmet, ohne dabei die Rolle der Gemeinschaften bei den Merkmalen der Streuprozesse zu berucksichtigen. Hier verallgemeinern wir das SIR-Modell von Epidemien durch die Einfuhrung einer Matrix von Gemeinschaftsansteckungsraten, um die heterogene Natur des Streuens zu erfassen, die durch die naturlichen Merkmale von Gemeinschaften definiert sind. Wir stellen fest, dass die Streufahigkeiten einer Gemeinschaft gegenuber einer anderen durch das interne Verhalten von Drittgemeinschaften beeinflusst wird. Unsere Ergebnisse bieten Einblicke in Systeme mit reichhaltigen Informationsstrukturen und in Populationen mit vielfaltigen Immunreaktionen.