Graph neural networks (GNN) are vital for analyzing real-world problems (e.g., network analysis, drug interaction, electronic design automation, e-commerce) that use graph models. However, efficient GNN acceleration faces with multiple challenges related to high and variable sparsity of input feature vectors, power-law degree distribution in the…

A research question that is of interest across many disciplines is whether and how relationships in a network are related to the attributes of the nodes of the network. In this dissertation, we propose two joint frameworks for modeling the relationship between the network and attributes. In the joint latent space model in Chapter 2, shared latent…

This dissertation is about a particular style of research. The philosophy of this style is that in order to scientifically understand deep learning, it is fruitful to investigate what happens when neural networks are trained on simple, mathematically well-defined tasks. Even though the training data is simple, the training algorithm can end up…

Few studies on teachers' social networks have extended their scopes from schools to online, leaving gaps and the potential to study how school and district colleagues as well as online-only peers can exert a network influence on teachers' online resource curation activities. These studies have underused the relational-event social-influence model…

The purpose of this study is to examine how land-grant universities engage with the public in the era of globalization; to explain the institutionalization of engagement processes accounting for the global context; and, to integrate this analysis into a Global Engagement Model for Land-Grant Universities (GEM) implementing a grounded theory…

Several daily phenomena around us can be modeled as time-evolving networks. Working with expressive and tractable models for the evolution of such networks can improve different prediction and decision-making tasks. While the literature has studied many approaches to model such networked phenomena partially, multiple gaps remain. This thesis is an…

The purpose of this Action Research study was to examine, understand, strengthen, and improve how virtual platforms can be used to support the challenges novice teachers face. This document will outline the study's objective for collecting data within the initial stages of this action research study. By fostering deeper relationships between…

The first part of this dissertation conducts a large-scale study comparing general and usage-based indices of syntactic complexity in L2 Mandarin writing samples across a wide range of proficiency levels. To do this, the Tool for the Automated Analysis of Syntactic Sophistication and Complexity (TAASSC; Kyle, 2016) was adapted for Mandarin by…

An estimated 10 out of every 1,000 children in preschool are expelled from childcare programs. The purpose of this qualitative instrumental multiple case study was to explore the experiences of childcare directors with preschool expulsion and their perceptions regarding the why and how the phenomenon and the nature of their role in supporting…

Social networks bring both opportunities and threats to the users. On one hand, social networks provide a platform for users to build online profiles, make connections with others beyond geographical boundaries, enjoy the "openness" of social networks to meet their intrinsic need of "self-presentation", explore and strengthen…

This dissertation describes a qualitative research study that grows our understanding of the career development experiences, supports, and barriers of social entrepreneurs who are gifted adults (SEGA) so that we may nurture the career development of future SEGA. Research questions for this study probed the career development experiences, supports,…

The purpose of this study is to create a model of tertiary vocational education in Kenya. Despite considerable progress in Kenya over the last 20 years, current education models, low attendance, and low academic proficiency levels preclude many vulnerable learners from becoming employable. Utilizing semi structured interviews of eight Kenyan…

Biomedical research increasingly relies on the analysis and visualization of a wide range of collected data. However, for certain research questions, such as those investigating the interconnectedness of biological elements, the sheer quantity and variety of data results in rather uninterpretable--this is especially true for network visualization,…

The underrepresentation of women in executive levels of higher education leadership has been discussed in the literature from a variety of viewpoints. In the context of Christian higher education, the focus of this study, women's underrepresentation has sometimes been compounded by the conservative theological tenets of some denominations…

This dissertation investigated how a certain type of organizational knowledge sharing, procedural knowledge transparency, affected innovation adoption rates of members of a corporate social network within a large Scandinavian organization, in its two years of activity. It also explored the mediation of these effects by different types of…