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 58 for “"Graph neural networks (GNNs)"”.
-
Using heterogeneous Graph Neural Networks(hGNN) to predict cell-cell communication
… (scRNA-seq) data. We evaluate the performance of Graph Neural Networks (GNNs) both with and without gene-gene edges, Contrastive Learning, and Variational Autoencoders (VAEs) across multiple datasets. Our study compares these methods and establishes benchmarks for assessing their effectiveness …
-
Graph Neural Networks for City Policy Recommendations as a Link Prediction Task
Graph Neural Networks (GNNs) have become a widely utilized tool in recommender systems in various contexts. While recommendation tasks can be approached using a multitude of data structures and types, graph-structured data is particularly well-suited for this domain, as graphs naturally capture a …
-
MACHINE LEARNING FOR TEMPORAL HETEROGENEOUS GRAPHS: PREDICTIVE METHODS, INTERPRETABILITY AND APPLICATIONS.
… predictive methods for temporal heterogeneous graphs by integrating modeling and tools from network science and graph deep learning. We introduce discrete-time graph learning architectures based on Graph Neural Networks (GNNs) and linear scoring functions tailored for forecasting dynamic, …
-
Log file anomaly detection using knowledge graphs and graph neural networks
… proposed representing log files as knowledge graphs (KGs) and using KG completion (KGC) techniques to predict new facts. However, current research in this area is limited, and there is no end-to-end system that includes both KG generation and KGC for log-based anomaly detection. In this study, …
-
Robust graph representation learning with structure-aware attention and self-supervised contrastive frameworks.
Graph-structured data is pervasive across domains such as social networks, biological systems, and information networks, yet effectively learning from such data remains a fundamental challenge in machine learning. My dissertation focuses on developing novel graph representation learning methods …
-
Designing Novel DNA-Binding Proteins with Generative Deep Learning
… molecules. The proposed methodology leverages Graph Neural Networks (GNNs) for encoding protein struc- tures and diffusion models for conditional sampling. The GNNs capture the intricate relationships between amino acids in the protein backbone, allowing for the effective encoding of structural …
-
Optimizing Out-Of-Memory Sparse-Dense Matrix Multiplication
… (SpMDM), with a focused application on graph machine learning workloads, such as graph neural networks (GNNs), though this work is general enough such that it should apply to any application tailored for running matrix multiplication workloads that cannot fit in memory. Specifically, we …
-
Explainable AI: A Unified Approach Based on Cooperative Game Theory
… interactions. Additionally, TreeSHAP-IQ and GraphSHAP-IQ improve model-specific computations for tree-based models and graph neural networks (GNNs), respectively. Recognizing the dynamic nature of real-world AI systems, we further develop incremental Permutation Feature Importance (iPFI) for …
-
Link Prediction on Distributed Systems
… these interactions, prompting the use of dynamic graph-based models, such as Graph Neural Networks (GNNs) and transformer-based architectures, for link prediction tasks. Despite their success, these models struggle with large-scale, temporal data and limited generalization capabilities. This …
-
On Counting Substructures with Graph Neural Networks
To achieve a graph representation, most Graph Neural Networks (GNNs) follow two steps: first, each graph is decomposed into a number of subgraphs (which we call the recursion step), and then the collection of subgraphs is encoded by several iterative pooling steps. While recently proposed …
-
Towards Efficient and Scalable Deep Learning on Graph-Structured Data
The practical deployment of Graph Neural Networks (GNNs), a primary form of deep learning on graphs, is hindered by intertwined challenges of effectiveness and scalability. This thesis, "Towards Effective and Scalable Deep Learning on Graph-Structured Data," proposes novel methodologies to address …
-
Faithful and fair generative explainers for graph neural networks
Graph Neural Networks (GNNs) have demonstrated remarkable effectiveness across various real-world applications; however, their underlying mechanisms remain a mystery. Explaining GNNs is crucial for understanding their complex underlying mechanisms, ensuring application safety, and enhancing model …
-
Towards an Efficient Network Intrusion Detection System for IoT Networks Leveraging Graph Neural Networks
… because they treat network flows independently. Graph Neural Networks (GNNs) have emerged as a promising alternative having the ability to capture the underlying network topology. However, existing approaches focus solely on either node or edge features, limiting their capacity to fully …
-
Power Failure Cascade Prediction using Machine Learning
… Further, we also propose a model based on graph neural networks (GNNs) that predicts cascades from the initial contingency and power injection values. We train the proposed models using a cascade sequence data pool generated from simulations. We then evaluate our models at various levels of …
-
Graph structures, random walks, and all that : learning graphs with jumping knowledge networks
Graph representation learning aims to extract high-level features from the graph structures and node features, in order to make predictions about the nodes and the graphs. Applications include predicting chemical properties of drugs, community detection in social networks, and modeling interactions …
-
Fast Partitioning for Distributed Graph Learning using Multi-level Label Propagation
Graph Neural Networks (GNNs) are a popular class of machine learning models that allow scientists to leverage machine learning techniques to perform inference on unstructured data. However, when graphs become too large, partitioning becomes necessary to allow for distributed computation. Standard …
-
Subgraph classification through neighborhood pooling
Subgraph classification is an emerging field in graph representation learning where the task is to classify a group of nodes (i.e., a subgraph) within a graph. Graph neural networks (GNNs) are the de facto solution for node, link, and graph-level tasks but fail to perform well on subgraph …
-
Crime Detection from Pre-crime Video Analysis
… diverse set of models including 3D Convolutional Neural Networks (CNNs), Graph Neural Networks (GNNs), Recurrent Neural Networks (RNNs), and a specially developed transformer architecture, the research systematically explores the impact of integrating additional contextual information into video …
-
From GNNs to sparse transformers: graph-based architectures for multi-hop question answering
… Sparse Transformers [7] have surpassed Graph Neural Networks (GNNs) as the state-of-the-art architecture for MHQA. Noting that the Transformer [4] is a particular message passing GNN, in this work we perform an architectural analysis and evaluation to investigate why the Transformer …
-
Graph feature engineering and coordinate-based learning for transferable and energy-efficient artificial intelligence
… framework for efficient and scalable graph representation learning is presented, emphasizing coordinate-based and explicit structural methods. The research addresses the limitations of Graph Neural Networks (GNNs) in resource-constrained environments, including edge devices and …
Page 1 of 3