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 26 for “"GraphSAGE"”.
-
Contrastive Loss in Recommendation Systems
… and Graph Sample and Aggregate (GraphSAGE), in the recommendation system on two categories of Amazon review datasets ( "All Beauty" and "Tools and Home Improvement"). The novelty of this work includes combining supervised and self-supervised learning through Weighted Approximate …
-
Scalable knowledge graph construction and inference on human genome variants
… and dealt with. We compare two GNN models, GraphSAGE and Graph Convolutional Network (GCN), to identify the range of raw scores it can belong to and the GraphSAGE model to identify the deleteriousness of a variant using different model hyperparameter settings. Through the experiments …
-
A Knowledge Graph-Based approach for modeling legislative texts: representation and document similarity analysis
… (ii) structure-aware KGs encoded via FastRP and GraphSAGE embeddings; and (iii) contextually enriched KGs also encoded via FastRP and GraphSAGE embeddings. Results using legislative proposals from the Legislative Assembly of Rio Grande do Norte (ALRN) show that while the text-based model achieved …
-
Modelado espacio-temporal con redes neuronales para la predicción de fenómenos ambientales
… Se proponen y comparan arquitecturas GNN (GCN, GraphSAGE, GAT) y variantes híbridas con CNN/LSTM/TCN/Transformers para la predicción de AOD550, calidad del aire urbana y contaminación acústica. La metodología integra reanálisis ERA5 y observaciones locales, con protocolos de validación …
-
Graph neural network approaches and real-time unsupervised learning for anomaly detection in vehicular networks
… Network (GCN), Graph Attention Network (GAT), GraphSAGE, Temporal GCN (T-GCN), Gated Convolutional LSTM (GConvLSTM), and Gated Convolutional GRU (GConvGRU). The GConvLSTM and GConvGRU models achieved the highest precision, recall, and F1-scores, with GraphSAGE and GAT providing competitive …
-
Some Mathematical Perspectives of Graph Neural Networks
… Neural Networks, Graph Attention Networks, GraphSAGE, and PinSAGE. Some special aspects of GNN training are also presented. Finally, we investigate a neighborhood sampling approach on PinSAGE to a product-user recommendation problem.
-
ANALYSIS OF LARGE SCALE URBAN TRANSPORTATION NETWORK USING URBAN TRAFFIC DATA
… link traffic speed is performed with the GraphSAGE models in urban road networks. Besides, the thesis also investigates the propagation of traffic congestion by first generating congested area with Markov random field, and therefore modeling the congestion probability with a collaborative …
-
Improved and domain specific model soups
… ogbn-products) and GNN architectures (GCN, GAT, GraphSAGE), LS achieves up to 1.2% accuracy improvement and 2.1X speedup, while PLS delivers a 24.5X speedup and 76% memory reduction without compromising accuracy. These findings validate that sophisticated, task-tailored souping strategies can …
-
Edge co-occurrence regularization for node classification
… using three GNN architectures: GCN, GraphSAGE, and H2GCN. Results show consistent improvements on homophilic graphs, with accuracy gains of 3-6% on Cora and CiteSeer. The method shows more modest gains on heterophilic datasets, suggesting its effectiveness is tied to graph structure. …
-
Scalable and Versatile Hardware Acceleration of Graph Neural Networks
… (GATs), graph convolutional networks (GCNs), GraphSAGE, GINConv, and DiffPool. It mitigates workload imbalance by (i) splitting vertex feature operands into blocks, (ii) reordering and redistributing computations, (iii) using a novel “flexible MAC” architecture. To maximize on-chip data reuse …
-
Accelerating GNN Inference on Multi-Core Systems
… to 3.35× and 3.20× speedups over DGL for GCN and GraphSAGE respectively, and even greater improvements over PyG, across a range of large-scale, high-dimensional graph datasets with diverse structural properties.
-
Learning and Reconstructing Conflicts in O-RAN
… Network (O-RAN). Specifically, we leverage GraphSAGE, an inductive learning framework, to dynamically learn the hidden relationships between xApps, control parameters, and Key Performance Indicators (KPIs). Our numerical results, based on a conflict model used in the Open Radio Access …
-
Graph Neural Network Architectures for interpretable I/O bottleneck analysis in high-performance computing systems
… I/O features. Graph Attention Networks (GAT) and GraphSAGE leverage this structure to learn from neighborhood information during prediction. A multi-method interpretability framework combining attention mechanisms, GNNExplainer, and Integrated Gradients provides robust bottleneck diagnosis through …
-
Beyond node-centric graph learning: advancing edge-aware GNNs for enhanced representation learning
… traditional node-centric baselines (GCN, GraphSAGE) in node load prediction tasks, achieving R² scores of up to 0.92. Error analysis reveals that our edge-aware approach is particularly effective at minimizing Root Mean Squared Error (RMSE), indicating superior capability in detecting …
-
Network-Based Gene Prioritization for Major Depressive Disorder Using Integrated Biological Data
… framework. Five models, including GCN, GCNII, GraphSAGE, APPNP, and Random Forest, are applied to prioritize candidate genes using a fixed set of positive genes and multiple independently sampled negative sets. While the models exhibit different prioritization behaviors, they consistently …
-
Data-Driven Bike-Share Ridership Prediction and Network Optimization
… customized Graph Neural Network framework using GraphSAGE is introduced for station-to-station ridership prediction, integrating network topology, sociodemographic features, and station attributes. Applied to Toronto, the model outperforms linear, spatial, and tree-based benchmarks, demonstrating …
-
Graph Neural Networks for Neighborhood Socioeconomic Modeling from High-Dimensional Census Data
… including Graph Convolutional Networks and GraphSAGE, to incorporate relational context through message passing. Third, hybrid models are developed by combining GNN-derived embeddings with original tabular census features and training downstream machine learning regressors. The framework is …
-
Advancing Bug Report Management: Graph-Based Modeling, Large Language Models, and Quality Improvement
… consists of Graph Sample and AggreGatE (GraphSAGE) and Graph Attention Networks, which outperform fine-tuned Bidirectional Encoder Representations from Transformers (BERT) on predict ing severity and priority of bug reports. Secondly, we focus on improving the quality of bug reports …
-
Graph neural networks for clinical risk prediction based on patient similarity graphs
… we introduce three new GNN solutions based on GraphSAGE, GAT, and Graph Transformer (GT) that address the challenges related to three identified literature gaps: multimodality, patient similarity, and interpretability. Our best model, the GT, ob tained an F1 score of 0.5361, resulting in a …
-
Real-Time Event-Driven Load Shedding for Power System Transient Stability Control using Deep Learning Techniques
… impairment on control cost. On top of those, a GraphSAGE-based ELS model is proposed to capture and embed the topological structure of power system into deep learning, which further improves the overall control performance of ELS. The proposed methodologies have been tested on New England 39 bus …
Page 1 of 2