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 20 of 96 for “"Graph neural network"”.
-
Graph matching by graph neural network
Graph matching or network alignment refers to the problem of matching two correlated graphs. This thesis presents a deep Q learning based method, which represents the matching process by a graph neural network. By breaking the symmetry, the parameterized graph neural network is able to capture a …
-
Optimizing Graph Neural Network Training on Large Graphs
Graphs can be used to represent many important classes of structured real-world data. For this reason, there has been an increase of research interest in various machine learning approaches to solve tasks such as link prediction and node property prediction. Graph Neural Network models demonstrate …
-
Explainable AI framework through Multi-Context Multi-Dimensional Graph Neural Network
… due to their inherent linearity. We adopted Graph Neural Networks (GNNs), a sophisticated machine learning paradigm adept at handling graph-based data to surmount these obstacles. GNNs displayed a flair for harnessing the relational dynamics inherent in complex systems such as social media, …
-
Optimizing Graph Neural Network Training on Large Graphs in A Distributed Setting
Graph neural networks (GNNs) are an important class of methods for leveraging the information present in graph structures to perform various learning tasks. Distributed GNNs can improve the performance of GNN execution by dividing computation among multiple machines and scale to large graphs by …
-
Understanding Neural Burst Patterns Through Graph Neural Network Explainability in Simulated Neuronal Networks
Spontaneous bursting activity in neural networks represents a fundamental mode of informationprocessing in the brain, yet the mechanisms triggering these synchronized events remain poorly understood. While graph-based representations of neural networks are established, discovering the specific …
-
A Graph Neural Network for pairwise surrogate modeling in population-based algorithms with tournament selection
… in a pairwise comparison. We demonstrated a Graph Neural Network (GNN) to be trained on number of pairs, then utilized to compare a pair of candidate solutions. To examine the efficacy of our model, we utilized the surrogate model on CEC2017 benchmarks in different dimensions. Moreover, the …
-
Dynamic graph neural network framework for real-time multi-modal data analysis and predictive modeling
In recent years, Graph Neural Networks (GNNs) have become increasingly prominent for analyzing complex, interconnected data across fields such as transportation, social networks, and cybersecurity. Despite their advancements, many existing GNN models struggle to capture the intricate interactions …
-
Graph neural network approaches and real-time unsupervised learning for anomaly detection in vehicular networks
… or impaired, remaining leading causes. Vehicular networks, as a core component of intelligent transportation systems (ITS), enable real-time vehicle–infrastructure communication through Cooperative Awareness Messages (CAMs), offering opportunities to detect anomalies in both driving behavior and …
-
Development of transferable equivariant graph neural network forcefields for enhanced exploration of molten salt systems
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms
-
Machine learning applications in astrophysics: Reduced-order modelling for chemical kinetics and galaxy merger reconstruction with graph neural network
… chemical kinetics solvers from user-specified networks, enabling simplified integration of customized chemistry in simulations. The combination of neural ordinary differential equations and autoencoders is shown to be a promising approach for reducing the complexity of chemical kinetics …
-
Scalability and interpretability of graph neural networks for small molecules
In this thesis I examine the use of graph neural networks for prediction tasks in chemistry with an emphasis on interpretable and scalable methods. I propose a novel kernel-inspired graph neural network architecture, called a subgraph matching neural network (SMNN), which is designed to have all …
-
Novel Machine Learning Models Based Uncertainty Estimation and Sequential Predictions for Blockchain Networks
… address to con- duct illicit activities over the network. Consequently, this double-edged sword technology urges the necessity of analysing blockchain data to detect illicit activities. In the existing literature, visual analytics have been widely used to gain useful insights from large-scale …
-
Enhancing Network Resilience through Machine Learning-powered Graph Combinatorial Optimization: Applications in Cyber Defense and Information Diffusion
With the burgeoning advancements of computing and network communication technologies, network infrastructures and their application environments have become increasingly complex. Due to the increased complexity, networks are more prone to hardware faults and highly susceptible to cyber-attacks. …
-
Spatiaalinen multiomiikka ja syväoppiminen: Datan haasteet ja menetelmäkehitys
… autoencoder, VAE), graafipohjaiset neuroverkot (graph neural network, GNN) sekä hybridimallit, jotka voivat yhdistellä useampaa eri arkkitehtuuria yhdeksi kokonaisuudeksi. Kirjallisuuskatsauksessa käsiteltyjen tutkimusten pohjalta on selvää, että syväoppimisen käyttö spatiaalisen …
-
Balancing Memory Efficiency and Accuracy in Spectral-Based Graph Transformers
… deep learning, yet transformer-based models for graph representation learning have not caught up to mainstream Graph Neural Network (GNN) variants. A major limitation is the large O(𝑛2) memory consumption of graph transformers, where 𝑛 is the number of nodes. Therefore, we develop a …
-
Diffusion Probabilistic Modeling of Protein Backbones in 3D for the Motif-Scaffolding problem
… backbone structures via an E(3)-equivariant graph neural network. We develop SMCDiff to efficiently sample scaffolds from this distribution conditioned on a given motif; our algorithm is the first to theoretically guarantee conditional samples from a diffusion model in the large-compute …
-
A Comprehensive Solution to Predict Short-term and Long-term user Intention with Environmental Context
… aspects, and items as nodes and edges of the graph neural network. This method entirely considers the close relation between user sentiment polarity change and item features, and the solution shows good performance when compared with the baseline model in the experiments.
-
Road Traffic Flow Prediction Using Aerial Imagery
… potential and feasibility of widespread drone networks. Among other tasks, monitoring road traffic flow is a task well-suited for such networks. While real-time traffic flow estimation systems have been explored at length and exist as commercial services, these systems have limited spatial …
-
IMPROVING MULTI-VARIATE TIME SERIES FORECASTING WITH DYNAMIC MULTI-HEAD ATTENTION ADJACENCY MATRIX
… allocation. Existing research, including neural network-based models and transformer-based models, has demonstrated high performance in learning temporal information. However, capturing spatial information within time series data remains a significant challenge. In this project, we …
Page 1 of 5