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"”.

  1. 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 …

    uiuc Repository record for Graph matching by graph neural network (opens in a new tab)

  2. 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 …

    mit Repository record for Optimizing Graph Neural Network Training on Large Graphs (opens in a new tab)

  3. 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, …

    umkc Repository record for Explainable AI framework through Multi-Context Multi-Dimensional Graph Neural Network (opens in a new tab)

  4. 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 …

    mit Repository record for Optimizing Graph Neural Network Training on Large Graphs in A Distributed Setting (opens in a new tab)

  5. 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 …

    washington Repository record for Understanding Neural Burst Patterns Through Graph Neural Network Explainability in Simulated Neuronal Networks (opens in a new tab)

  6. 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 …

    uoit Repository record for A Graph Neural Network for pairwise surrogate modeling in population-based algorithms with tournament selection (opens in a new tab)

  7. 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 …

    umkc Repository record for Dynamic graph neural network framework for real-time multi-modal data analysis and predictive modeling (opens in a new tab)

  8. 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 …

    umkc Repository record for Graph neural network approaches and real-time unsupervised learning for anomaly detection in vehicular networks (opens in a new tab)

  9. 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

    uiuc Repository record for Development of transferable equivariant graph neural network forcefields for enhanced exploration of molten salt systems (opens in a new tab)

  10. 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 …

    uiuc Repository record for Machine learning applications in astrophysics: Reduced-order modelling for chemical kinetics and galaxy merger reconstruction with graph neural network (opens in a new tab)

  11. 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 …

    mit Repository record for Scalability and interpretability of graph neural networks for small molecules (opens in a new tab)

  12. 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 …

    bournemouth Repository record for Novel Machine Learning Models Based Uncertainty Estimation and Sequential Predictions for Blockchain Networks (opens in a new tab)

  13. 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. …

    adelaide Repository record for Enhancing Network Resilience through Machine Learning-powered Graph Combinatorial Optimization: Applications in Cyber Defense and Information Diffusion (opens in a new tab)

  14. 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 …

    helsinki Repository record for Spatiaalinen multiomiikka ja syväoppiminen: Datan haasteet ja menetelmäkehitys (opens in a new tab)

  15. 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 …

    mit Repository record for Balancing Memory Efficiency and Accuracy in Spectral-Based Graph Transformers (opens in a new tab)

  16. 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 …

    mit Repository record for Diffusion Probabilistic Modeling of Protein Backbones in 3D for the Motif-Scaffolding problem (opens in a new tab)

  17. 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.

    carleton Repository record for A Comprehensive Solution to Predict Short-term and Long-term user Intention with Environmental Context (opens in a new tab)

  18. 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 …

    mit Repository record for Road Traffic Flow Prediction Using Aerial Imagery (opens in a new tab)

  19. 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 …

    ecu Repository record for IMPROVING MULTI-VARIATE TIME SERIES FORECASTING WITH DYNAMIC MULTI-HEAD ATTENTION ADJACENCY MATRIX (opens in a new tab)

Page 1 of 5