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 444 for “"GNN"”.

  1. Composable Algorithms for Scalable GNN Dataloading

    Training Graph Neural Networks (GNNs) at a large scale requires significant computational resources. One of the most effective ways to reduce resource requirements is minibatch training coupled with graph sampling. Existing methods encounter a significant bottleneck to scaling due to the …

    gatech Repository record for Composable Algorithms for Scalable GNN Dataloading (opens in a new tab)

  2. ID-GNN: Unsupervised Graph Neural Network

    … as node classification. Experiments show that ID-GNN is within 3% of the node classification accuracy of state-of-the-art methods on heterophilic graphs.

    boise Repository record for ID-GNN: Unsupervised Graph Neural Network (opens in a new tab)

  3. Accelerating GNN Inference on Multi-Core Systems

    Graph Neural Networks (GNNs) are becoming increasingly popular, with their applications expanding across diverse domains. As the scale of graph data continues to grow, including larger numbers of nodes, edges, and higher embedding dimensions, standardized libraries such as DGL and PyG have been …

    wustl Repository record for Accelerating GNN Inference on Multi-Core Systems (opens in a new tab)

  4. GNN-based Handover Management in 5G Vehicular Networks

    … 5G environments using graph neural networks (GNNs). TH-GCN predicts optimal connections and the best handover choices by modeling vehicles and towers as nodes in a dynamic graph, with connections depicted as edges and incorporating features like signal quality, vehicle mobility, throughput, …

    brock Repository record for GNN-based Handover Management in 5G Vehicular Networks (opens in a new tab)

  5. An Improved GNN-Reasoner for Game Description Language

    … on Prolog or Propnet. The introduction of the GNN-Reasoner [9] shows a promising approach of using neural networks by employing a graph-based approach for game rules and state representation, though it faced challenges such as dataset feature design and inference task completion. Addressing …

    auckland-tech Repository record for An Improved GNN-Reasoner for Game Description Language (opens in a new tab)

  6. Scaling Parallel Full-graph GNN Training to Thousands of GPUs

    … of a GPU due to their sheer size, and using GNNs on them requires techniques such as mini-batch sampling to scale. However, this can lead to reduced accuracy in some cases, and sampling and data transfer from the CPU to the GPU can also slow down training. On the other hand, distributed …

    maryland Repository record for Scaling Parallel Full-graph GNN Training to Thousands of GPUs (opens in a new tab)

  7. GNN Convergence and Accuracy Analysis on Contextual Stochastic Block Models

    … the performance of Graph Neural Networks (GNNs). In this thesis, I prove how inducing symmetries on general, nonlinear GNNs improves their cross entropy on cSBMs, and I derive the limiting accuracy of linear Graph Convolutional Networks (GCNs) on cSBMs. I use these results to derive the …

    byu Repository record for GNN Convergence and Accuracy Analysis on Contextual Stochastic Block Models (opens in a new tab) Download PDF for GNN Convergence and Accuracy Analysis on Contextual Stochastic Block Models (opens in a new tab)

  8. Offloading the sampling stage of GNN training to smart storage

    Graph Neural Networks (GNNs) have emerged as a robust model for machine learning, addressing complex graph-structured data, in contrast to traditional deep learning techniques primarily used for image and text data. However, the scalability of GNNs on large graphs with billions of nodes and …

    bu Repository record for Offloading the sampling stage of GNN training to smart storage (opens in a new tab)

  9. GNN-based End-to-end Delay Prediction in Software Defined Networking

    … topologies and apply a Graph Neural Network (GNN)-based model, Spatial-Temporal Graph Convolutional Network (STGCN), to predict end-to-end packet delay on this formulation. The evaluation uses STGCN to compare with other machine learning methods: Multiple Linear Regression (MLR), Extreme …

    ottawa-retro Repository record for GNN-based End-to-end Delay Prediction in Software Defined Networking (opens in a new tab)

  10. Sampling a Subset of Chemical Space with GNN-Based Generative Models

    … use in drug discovery is graph neural networks (GNN:s). This thesis evaluates 6 GNN models for use in molecular graph generation. The evaluation is based on a benchmark introduced by Arús-Pous et al. [1], which measures how well models sample a subset of chemical space. The models are also …

    chalmers Repository record for Sampling a Subset of Chemical Space with GNN-Based Generative Models (opens in a new tab)

  11. Lane-changing prediction using GNN-LSTM architecture based on surrounding vehicle behavior

    … Graph Neural Networks-Long Short-Term Memory (GNN-LSTM) hybrid deep learning model for predicting lane-change maneuvers from trajectory data using comprehensive features of surrounding vehicles, with prediction horizon times extending up to 5 seconds ahead. The proposed GNN-LSTM architecture …

    umn Repository record for Lane-changing prediction using GNN-LSTM architecture based on surrounding vehicle behavior (opens in a new tab)

  12. GNN-based social media sentiment analysis for stock market forecasting and trading

    … approach that leverages Graph Neural Networks (GNNs) for sentiment analysis to enhance stock market prediction and trading strategy. By integrating social media sentiment analysis with traditional financial indicators, I develop a comprehensive model that more accurately captures market …

    bristol Repository record for GNN-based social media sentiment analysis for stock market forecasting and trading (opens in a new tab) Download PDF for GNN-based social media sentiment analysis for stock market forecasting and trading (opens in a new tab)

  13. Scalable and Reliable GNN-based Network Traffic Management in Software-Defined Vehicular Networks

    … and global tiers) with graph neural networks(GNN) for proactive traffic steering and RSU load balancing. Control objectives target stability, cluster longevity, and load fairness through a multi-objective training regime. A spatiotemporal GNN predicts short-horizon network states on …

    brock Repository record for Scalable and Reliable GNN-based Network Traffic Management in Software-Defined Vehicular Networks (opens in a new tab)

  14. Enhancing the Performance of GNN and Utilizing 3D Instance Segmentation for Ligand Binding Site Prediction

    … We employ and improve Graph Neural Networks (GNNs) and innovative 3D point cloud instance segmentation to refine and advance LBS prediction methods. This research demonstrates significant enhancements in predictive accuracy by evaluating these methods on widely used datasets. Our novel …

    washington Repository record for Enhancing the Performance of GNN and Utilizing 3D Instance Segmentation for Ligand Binding Site Prediction (opens in a new tab)

  15. Machine Learning-Augmented DAG-BFT Consensus Systems: GNN and RL-driven Adaptive, Scalable, Fault-tolerant Protocols

    … DAGWise, employs Graph Neural Networks (GNNs) and Structural Equation Models (SEMs) to compute embeddings from local DAG views. These embeddings capture causal relationships among blocks and proposer behaviors, enabling validators to perform leader scoring, message prioritization, and …

    houston Repository record for Machine Learning-Augmented DAG-BFT Consensus Systems: GNN and RL-driven Adaptive, Scalable, Fault-tolerant Protocols (opens in a new tab) Embargoed until 2027-12-01

  16. Machine Learning-Augmented DAG-BFT Consensus Systems: GNN and RL-driven Adaptive, Scalable, Fault-tolerant Protocols

    … DAGWise, employs Graph Neural Networks (GNNs) and Structural Equation Models (SEMs) to compute embeddings from local DAG views. These embeddings capture causal relationships among blocks and proposer behaviors, enabling validators to perform leader scoring, message prioritization, and …

    houston Repository record for Machine Learning-Augmented DAG-BFT Consensus Systems: GNN and RL-driven Adaptive, Scalable, Fault-tolerant Protocols (opens in a new tab) Embargoed until 2027-08-01

Page 1 of 23