Representation Learning techniques play a crucial role in a wide variety of Deep Learning applications. From Language Generation to Link Prediction on Graphs, learned numerical vector representations often build the foundation for numerous downstream tasks. In Natural Language Processing, word embeddings are contextualized and depend on their current context. This useful property reflects how words can have different meanings based on their neighboring words. In Knowledge Graph Embedding (KGE) approaches, static vector representations are still the dominant approach. While this is sufficient for applications where the underlying Knowledge Graph (KG) mainly stores static information, it becomes a disadvantage when dynamic entity behavior needs to be modelled. To address this issue, KGE approaches would need to model dynamic entities by incorporating situational and sequential context into the vector representations of entities. Analogous to contextualised word embeddings, this would allow entity embeddings to change depending on their history and current situational factors. Therefore, this thesis provides a description of how to transform static KGE approaches to contextualised dynamic approaches and how the specific characteristics of different dynamic scenarios are need to be taken into consideration. As a starting point, we conduct empirical studies that attempt to integrate sequential and situational context into static KG embeddings and investigate the limitations of the different approaches. In a second step, the identified limitations serve as guidance for developing a framework that enables KG embeddings to become truly dynamic, taking into account both the current situation and the past interactions of an entity. The two main contributions in this step are the introduction of the temporally contextualized Knowledge Graph formalism and the corresponding RETRA framework which realizes the contextualisation of entity embeddings. Finally, we demonstrate how situational contextualisation can be realized even in static environments, where all object entities are passive at all times. For this, we introduce a novel task that requires the combination of multiple context modalities and their integration with a KG based view on entity behavior.

This thesis explores local and global normal and Edgeworth approximations for symmetric binomial distributions. Further, it examines the normal approximation of convolution powers of continuous and discrete uniform distributions. We obtain the optimal constant in the local central limit theorem for symmetric binomial distributions and its analogs in higher-order Edgeworth approximation. Further, we offer a novel proof for the known optimal constant in the global central limit theorem for symmetric binomial distributions using Fourier inversion. We also consider the effect of simple continuity correction in the global central limit theorem for symmetric binomial distributions. Here, and in higher-order Edgeworth approximation, we found optimal constants and asymptotically sharp bounds on the approximation error. Furthermore, we prove asymptotically sharp bounds on the error in the local case of a relative normal approximation to symmetric binomial distributions. Additionally, we provide asymptotically sharp bounds on the approximation error in the local central limit theorem for convolution powers of continuous and discrete uniform distributions. Our methods include Fourier inversion formulae, explicit inequalities, and Edgeworth expansions, some of which may be of independent interest.

Mindfulness is a popular technique that helps people to get closer to their self. However, recent findings indicate that mindfulness may not benefit everybody. In the present research, we hypothesized that mindfulness promotes alienation from the self among individuals with low abilities to self-regulate affect (state-oriented individuals) but not among individuals with high abilities to self-regulate affect (action-oriented individuals). In two studies with participants who were mostly naïve to mindfulness practices (70% indicated no experience; N1 = 126, 42 men, 84 women, 0 diverse, aged 17–86 years, Mage = 31.87; N2 = 108, 30 men, 75 women, 3 diverse, aged 17–69 years, Mage = 28.00), we tested a mindfulness group (five-minute mindfulness exercise) against a control group (five-minute text reading). We operationalized alienation as lower consistency in repeated preference judgments and a lower tendency to adopt intrinsic over extrinsic goal recommendations. Results showed that, among state-oriented participants, mindfulness led to significantly lower consistency of preference judgments (Study 1) and lower adoption of intrinsic over extrinsic goals (Study 2) compared to text reading. The alienating effect was absent among action-oriented participants. Thus, mindfulness practice may alienate psychologically vulnerable people from their self and hamper access to preferences and intrinsic goals. We discuss our findings within Personality-Systems-Interactions (PSI) theory.