Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 13 of 13 for “"graph transformers"”.
-
Detecting unauthorized access to computer networks through graph transformers
… Since computer network interactions form graph-structured data, graph-based algorithms, such as Graph Neural Networks (GNNs) and Graph Transformers (GTs), can be employed to detect anomalous interactions indicative of attacks within the computer net- works. However, the effectiveness of …
-
Advancing Expressibility and Scalability in Graph Learning
Graph learning models have become the dominant approach for learning from graph-structured data, yet two fundamental challenges persist: expressiveness and scalability. Advances in model expressiveness often compromise scalability, underscoring the need for holistic approaches that address both …
-
Learning-Based Task Assignment for Automated Guided Vehicles: Applying graph neural networks to optimise task assignment in an online warehouse environment
… The warehouse environment is modelled as a graph, and a Graph Neural Network (GNN) policy is trained using Proximal Policy Optimization (PPO) to assign tasks to the vehicle fleet. To capture the complex topology of the facility, which is characterized by long-range spatial configurations and …
-
Improving protein structure prediction with multicom
… to experimental methods such as X-ray crystallography and cryo-electron microscopy. Despite advancements in deep learning, including methods like AlphaFold2, challenges remain in predicting protein tertiary and quaternary structures and assessing model quality due to limited evolutionary data …
-
Virtual nodes for graph neural networks : techniques, impact, and theoretical analysis
This thesis investigates virtual nodes (VNs), a graph augmentation technique that improves the performance of Graph Neural Networks (GNNs). Although VNs have been widely used in practice, their theoretical foundations and systematic evaluation remain limited. To address this gap, we propose the …
-
Artificial Intelligence-Enabled Digital Resilience Framework: A Computational Design Science Approach
… framework for digital resilience. Essay 1 uses graph autoencoders with a specialized masking mechanism to detect how security vulnerabilities in payment gateways propagate to merchant applications. Essay 2 utilizes a dual-view graph autoencoder with graph transformers and cross-type attention to …
-
Beyond node-centric graph learning: advancing edge-aware GNNs for enhanced representation learning
Graph Neural Networks (GNNs) have achieved state-of-the-art performance in representation learning, yet they predominantly treat edges as auxiliary structures for message passing, systematically overlooking their potential as primary informational entities. This thesis investigates the hypothesis …
-
Effective and Efficient Graph Foundation Model
Graph data has emerged as a central component in numerous real-world applications, spanning recommender systems, drug discovery, social networking, and traffic forecasting. While traditional and modern graph learning techniques—ranging from graph kernels to Graph Neural Networks (GNNs) and graph …
-
Artificial Intelligence-Enabled Vulnerability Analysis and Management for IT Infrastructure: A Computational Design Science Approach
… remediation strategies. Essay III utilizes graph contrastive learning and graph transformers to secure software deployments in IT infrastructure by replacing vulnerable software with secure alternatives. Each essay offers valuable practical implications for cybersecurity analysts, IT …
-
PathFormer: Interpretable and Powerful Graph Transformer for Gene Network Analysis
… active research area in Bioinformatics. Although graph neural networks (GNNs) have achieved impressive performance on various graph-based real-world applications such as recommendation systems and social network analysis, applying GNNs in gene-network-based Bioinformatical tasks is still …
-
LEARNING BOTH EXPERT AND UNIVERSAL KNOWLEDGE USING TRANSFORMERS
… long-range relation modeling. Further, Transformers have proved effective for learning universal knowledge at scale, and representative models are BERT, GPT, and their subsequent variants. It is observed that the Transformer is more tolerant to the convergence plateau and is capable of …
-
GASTON: Graph-Aware Social Transformer for Online Networks
… this limitation, this thesis proposes GASTON (Graph-Aware Social Transformer for Online Networks), a graph learning framework designed to capture the essence of online social networks. It does so by modeling connections between all online entities, such as users, communities, and text. This …