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 73 for “"GNNs"”.
-
From GNNs to sparse transformers: graph-based architectures for multi-hop question answering
… [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 outperforms other GNNs on …
-
Forecasting without sequences: graph representations for dynamic systems in finance and beyond using GNNs
Submission published under a 24 month embargo labeled 'U of I Access', the embargo will last until 2027-08-01
-
Structural performance evaluation of concrete arch dams using ambient vibration monitoring and GNNS systems
Societies around the world are heavily dependent on civil engineering infrastructures such as concrete dams that provide necessities such as water supply for irrigation, hydroelectric power generation and prevention of floods. As a result, it is important to ensure that concrete dams are protected …
-
Geometric Deep Learning for Healthcare Applications
… the application of Graph Neural Networks (GNNs), a subset of Geometric Deep Learning methods, for medical image analysis and causal structure learning. Tracking the progression of pathologies in chest radiography poses several challenges in anatomical motion estimation and image …
-
Practical processing and acceleration of graph neural networks
… the proven potential of graph neural networks (GNNs) and the vast space of possible applications, it is natural to turn our attention towards practical issues that arise when we aim to deploy these models beyond a research context. One primary concern is efficiency: how do we design GNNs that …
-
Weisfeiler-Leman graph kernels for the out-of-distribution characterization of graph structured data
… and power of Graph Neural Networks (GNNs) without introducing a new model architecture. Within existing GNN research, strong claims of out-of-distribution (OOD) generalizability are frequently made, but these claims fail when exposed to real-world data. We propose existing standards …
-
Sampling Methods for Fast and Versatile GNN Training
Graph neural networks (GNNs) have become a commonly used class of machine learning models that achieve state-of-the-art performance in various applications. A prevalent and effective approach for applying GNNs on large datasets involves mini-batch training with sampled neighborhoods. Numerous …
-
BEYOND LOCAL NEIGHBORHOODS: LEVERAGING INFORMATIVE NODES FOR IMPROVED GRAPH NEURAL NETWORKS PERFORMANCE
… (graph classification), graph neural networks (GNNs) serve as a powerful tool. Most GNNs utilize a message-passing scheme to aggregate information from neighboring nodes. This localized aggregation allows the network to learn representations that incorporate the context of each node, thereby …
-
Towards Efficient and Scalable Deep Learning on Graph-Structured Data
… 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 …
-
Subgraph classification through neighborhood pooling
… 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 classification tasks. Even GNNs tailored for graph classification are not directly transferable to subgraph classification as they ignore the …
-
Using heterogeneous Graph Neural Networks(hGNN) to predict cell-cell communication
… 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 beyond traditional case …
-
Medical Image Analysis Based on Graph Machine Learning and Variational Methods
… novel approach utilizing Graph Neural Networks (GNNs) that incorporate both spectral and spatial insights for segmentation. By leveraging various supervoxel creation methods such as VCCS, SLIC, Watershed, Meanshift, and Felzenszwalb-Huttenlocher, we structured 3D MRI images into a graph format. …
-
Robust graph representation learning with structure-aware attention and self-supervised contrastive frameworks.
… attention-based Graph Neural Networks (GNNs) and their variants, designing structure-aware and contrastive learning strategies to capture both local and global dependencies in graphs. Through extensive experiments on benchmark and real-world datasets, I demonstrate how these methods …
-
Designing Novel DNA-Binding Proteins with Generative Deep Learning
… 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 information relevant …
-
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 …
-
Graph Neural Networks for Multi-Agent Learning
… as special cases under graph neural networks (GNNs), a framework for operating over any graph-structured data. Taking advantage of relational inductive biases, GNNs use local filters to learn functions that generalise over high-dimensional data. They are particularly useful in the context of …
-
Link Prediction on Distributed Systems
… 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 research addresses these challenges by developing a …
-
On Counting Substructures with Graph Neural Networks
… 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 higher-order networks …
-
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 …
-
Deep Graph Representation Learning and its Application on Graph Clustering
… of the development of Graph Neural Networks (GNNs). However, there are still several crucial challenges that the field faces, including in (semi-)supervised DGL, self-supervised DGL, and DGL-based graph clustering. In this thesis, I proposed three models to address the problems in these three …
Page 1 of 4