UWSpace

UWSpace is the University of Waterloo’s institutional repository for the free, secure, and long-term home of research produced by faculty, students, and staff.

Depositing Theses/Dissertations or Research to UWSpace

Are you a Graduate Student depositing your thesis to UWSpace? See our Thesis Deposit Help and UWSpace Thesis FAQ pages to learn more.

Are you a Faculty or Staff member depositing research to UWSpace? See our Waterloo Research Deposit Help and Self-Archiving pages to learn more.

Photo by Waterloo staff
 

Recent Submissions

Item
Developing Quality Indicators for Home-based Teleconsultation in Secondary Stroke Prevention
(University of Waterloo, 2024-12-02) Meng, Guangxia
home-based teleconsultation service quality patient satisfaction quality indicators secondary stroke prevention
Item
The Sun Will Shine Again: On Populist Contagion of New and Establishment Parties in the Dutch National Elections of the 21st Century
(University of Waterloo, 2024-12-02) van Mierlo, Kevin R.O.
Twenty-one years after the murder on Pim Fortuyn, the right-wing populist Freedom Party (Partij voor de Vrijheid; PVV) won a plurality in the 2023 Dutch national election after long-term PM Mark Rutte announced that he would not run for re-election. This study serves as a contribution to Rooduijn’s ‘A Populist Zeitgeist?’ study (2014), looking into the spread of right-wing populist rhetoric throughout the Dutch party system since 2002. More specifically, this study looks at the contagion of populist rhetoric on the three establishment (‘winner’) parties (PvdA, VVD, CDA) and three new but successful (‘savior’) parties, compared to two well-known populist parties (LPF, PVV). This content analysis study uses a blend between Hawkins’ (2009) wholistic grading rubric and Rooduijn et al. (2014) paragraph-level coding in order to assess the amount and type of populist rhetoric in the selected party manifestos of the 2002, 2010, and 2023 election years. The qualitative discourse methods used shows that, in line with Rooduijn and colleague’s (2014) findings, that there still is no change in the absence of a populist Zeitgeist. The significance of these findings is in the enrichment of the understanding of Dutch populism after the PVV’s electoral win in 2023.
Item
QAVSA: Question Answering Using Vector Symbolic Algebras
(University of Waterloo, 2024-11-29) Laube, Ryan
With the advancement of large pretrained language models (PLMs), many question answering (QA) benchmarks have been developed in order to evaluate the capabilities of these models. Augmenting PLMs with external knowledge in the form of Knowledge Graphs (KGs) has been a popular method to improve their question-answering capabilities, and a common method to incorporate KGs is to use Graph Neural Networks (GNNs). As an alternative to GNNs for augmenting PLMs, we propose a novel graph reasoning module using Vector Symbolic Algebra (VSA) graph representations and a k-layer MLP. We demonstrate that our VSA-based model performs as well as QA-GNN, a model combining a PLM and a GNN-module, on 3 multiple-choice question answering (MCQA) datasets. Our model has a simpler architecture than QA-GNN, converges 37% faster during training, and has constant memory requirements as the size of the knowledge graphs increase. Furthermore, a novel method to analyze the VSA-based outputs of QAVSA is presented.
Item
Statistical Foundations for Learning on Graphs
(University of Waterloo, 2024-11-27) Baranwal, Aseem
Graph Neural Networks are one of the most popular architectures used to solve classification problems on data where entities have attribute information accompanied by relational information. Among them, Graph Convolutional Networks and Graph Attention Networks are two of the most popular GNN architectures. In this thesis, I present a statistical framework for understanding node classification on feature-rich relational data. First, I use the framework to study the generalization error and the effects of existing neural network architectures, namely, graph convolutions and graph attention on the Contextual Stochastic Block Model in the regime where the average degree of a node is at least order log squared n in the number of nodes n. Second, I propose a notion of asymptotic local optimality for node classification tasks and design a GNN architecture that is provably optimal in this notion, for the sparse regime, i.e., average degree O(1). In the first part, I present a rigorous theoretical understanding of the effects of graph convolutions in neural networks through the node classification problem of a non-linearly separable Gaussian mixture model coupled with a stochastic block model. First, I identify two quantities corresponding to the signal from the two sources of information: the graph, and the node features, followed by a result that shows that a single graph convolution expands the regime of the distance between the means where multi-layer networks can classify the data by a factor of up to one over square root of the expected degree of a node. Second, I show that with a slightly stronger graph density, two graph convolutions improve this factor to up to 1/sqrt{n}, where n is the number of nodes in the graph. This set of results provides both theoretical and empirical insights into the performance of graph convolutions placed in different combinations among the layers of a neural network, concluding that the performance is mutually similar for all combinations of the placement. In the second part, the analysis of graph attention is provided, where the main result states that in a well-defined ``hard'' regime, every attention mechanism fails to distinguish the intra-class edges from the inter-class edges. In addition, if the signal in the node attributes is sufficiently weak, graph attention convolution cannot perfectly classify the nodes even if the intra-class edges are separable from the inter-class edges. In the third part, I study the node classification problem on feature-decorated graphs in the sparse setting, i.e., when the expected degree of a node is O(1) in the number of nodes, in the fixed-dimensional asymptotic regime, i.e., the dimension of the feature data is fixed while the number of nodes is large. Such graphs are typically known to be locally tree-like. Here, I introduce a notion of Bayes optimality for node classification tasks, called asymptotic local Bayes optimality, and compute the optimal classifier according to this criterion for a fairly general statistical data model with arbitrary distributions of the node features and edge connectivity. The optimal classifier is implementable using a message-passing graph neural network architecture. This is followed by a result that precisely computes the generalization error of this optimal classifier, and compares its performance statistically against existing learning methods on a well-studied data model with naturally identifiable signal-to-noise ratios (SNRs). We find that the optimal message-passing architecture interpolates between a standard MLP in the regime of low graph signal and a typical graph convolutional layer in the regime of high graph signal. Furthermore, I provide a corresponding non-asymptotic result that demonstrates the practical potential of the asymptotically optimal classifier.
Item
Culture Clash: When Deceptive Design Meets Diverse Player Expectations
(Association for Computing Machinery, 2024-10-14) Hadan, Hilda; Sgandurra, Sabrina; Zhang-Kennedy, Leah; Nacke, Lennart
Deceptive game designs that manipulate players are increasingly common in the gaming industry, but the impact on players is not well studied. While studies have revealed player frustration, there is a gap in understanding how cultural attributes affect the impact of deceptive design in games. This paper proposes a new research direction on the connection between the representation of culture in games and player response to deceptive designs. We believe that understanding the interplay between cultural attributes and deceptive design can inform the creation of games that are ethical and entertaining for players around the globe.