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 14 of 14 for “"Graph dataset"”.
-
Empowering Graph Neural Networks from a Data-Centric View
… Intelligence (AI) require dealing with graph data, ranging from biology and chemistry to finance and education. As powerful learning tools for graph inputs, graph neural networks (GNNs) have demonstrated remarkable performance in various applications such as recommender systems and drug …
-
Selectivty Estimation on Big Data
Many real-world applications model data as record dataset and treat the relationships among data as a graph. There are significant research efforts devoting towards efficiently and effectively managing and analysing record dataset and graph dataset. Among them, applying similarity search in massive …
-
Accelerating large scale Graph Neural Network training using SmartSSD
Graph Neural Network (GNN) is a type of neural network that processes data structured as graphs. It excels at capturing complex relationships and dependencies between nodes within the graph. GNNs are increasingly significant, with numerous applications in the real world, such as social network …
-
A Study on Privacy Preserving Data Publishing With Differential Privacy
… formats such as Numerical and Categorical data, Graph Data, Tree-Structured data and so on. For preventing these data from being illegally exploited and protect it from privacy threats, it is required to apply an efficient privacy model over sensitive data. There have been a great number of …
-
Metapath of Thoughts: Verbalized Metapaths in Heterogeneous Graph as Contextual Augmentation to LLM
Heterogeneous graph neural networks (HGNNs) excel in cap- turing graph topology and structural information. However, they are ineffective in processing the textual components present in nodes and edges and thus producing suboptimal performance in downstream tasks such as node-classification. …
-
Personalized Distributed Machine Learning With Graphs
Graph structure pervades modern distributed learning: devices are naturally linkedthrough communication, resource, and data-similarity graphs, while the data they col- lect are often graphs themselves. This thesis shows that explicitly modeling both layers of structure unlocks accurate, efficient, …
-
Analysis of Current Flows in Electrical Networks for Error-Tolerant Graph Matching
… one thing in common: they can be represented as graphs. The need to analyze, compare, and classify graph datasets has become more evident over the last decade. The graph isomorphism problem is known to belong to the NP class, and the subgraph isomorphism problem is known to be an NP-complete …
-
Improved Neighbourhood Search-Based Methods for Graph Layout
Graph drawing, or the automatic layout of graphs, is a challenging problem. There are several search-based methods for graph drawing that are based on optimising a fitness function which is formed from a weighted sum of multiple criteria. This thesis proposes a new neighbourhood search-based method …
-
Resilience through Cyber-Layer Defense in Digital Substations
… is validated using an ATTandCK-based attack-graph dataset. Building upon the proposed technologies for digital substations, this dissertation extends cyber-layer defense to another emerging CPS, Artificial Intelligence Data Centers (AIDCs), whose manipulation as mega-loads can impose …
-
Detecting Illicit Bitcoin Transactions on the Dark Web
… increasingly dense and noisy Bitcoin transaction graphs. This thesis investigates whether, and how, blockchain analytics and machine learning can help detect illicit transactions on Bitcoin networks. The first part of the thesis is a systematic literature review of recent contributions from …
-
Novel approaches for learning representations
… this dissertation, I build off of semi-implicit graph variational auto-encoders to capture higher-order statistics in the latent features of a graph dataset. Indeed, I seek to address this by incorporating hyperbolic geometry in the latent space via a Poincaré embedding to efficiently represent …
-
Unsupervised Graph Neural Networks: Training Strategies and Evaluation Principles
Attributed graphs are the fundamental data representation that captures the dual dimensionality of structural connectivity and feature information. The task of community detection to find collections of similar nodes within the graph. Identifying the latent communities in a network with associated …
-
Optimizing graph query performance by indexing and caching
Subgraph/supergraph queries, though central to graph analytics, are costly as they entail the NP-Complete problem of subgraph isomorphism. To expedite graph query processing, the community has contributed a wealth of approaches that gradually form two categories, i.e., heuristic subgraph …
-
Towards the Next Generation Highly Scalable Distributed Machine Learning
… of gradients for synchronization. The emerging Graph Neural Networks (GNNs) usually have larger memory footprints compared to DNNs. Graph feature compression is a promising approach to accelerate GNN training by significantly reducing the memory footprint and PCIe bandwidth requirement so that …