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 20 for “"Adaptive graph"”.
-
HARDWARE-SOFTWARE CO-DESIGN FOR ACCELERATING GRAPH PROCESSING AND GNNS: FROM EDGE TO CLOUD
… on transforming the execution paradigms of graph workloads through hardware–software co-design and algorithmic innovations. Graph applications are characterized by irregular memory access and sparse computation, which limit the efficiency of traditional processors across diverse deployment …
-
MULTI-ROBOT RELIABLE NAVIGATION IN UNCERTAIN TOPOLOGICAL ENVIRONMENTS WITH GRAPH ATTENTION NETWORKS
… Process framework and introduce the Dynamic Adaptive Graph Embedding method to capture the evolving nature of the navigation task. We further enhance each robot's policy learning process by integrating deep reinforcement learning with Graph Attention Networks (GAT), leveraging self-attention …
-
Graph Based Deep Reinforcement Learning Aided by Transformers for Multi-Agent Cooperation
… propose an innovative framework that integrates Graph Neural Networks (GNNs), Deep Reinforcement Learning (DRL), and transformer-based mechanisms for enhanced multi-agent coordination and collective task ex- ecution. My approach leverages GNNs to model agent-agent and agent-goal interactions …
-
Factoring over probability simplices : from theory to applications
… tensor factorization models and to an adaptive graph-regularized denoising method for spatial transcriptomics, where the regularization evolves with the solution. Theoretically, we investigate why NMF methods work well despite non-convexity. Drawing inspiration from the benign geometry …
-
Estimation of Reconfigurable Intelligent Surface (RIS) Coefficients in Multi-User NOMA Systems Using Graph Neural Networks (GNNs)
… propagation links. This thesis investigates adaptive graph-based learning methods for RIS phase estimation in RIS-NOMA systems. The proposed framework represents the RIS-NOMA environment as a graph whose nodes correspond to the base station, RIS elements, and users, while edges describe …
-
Nonparametric estimation in high dimensions with applications to transcriptomics data
… The method – Spatial Transcriptomics via Adaptive Regularization and Kernels (STARK) – augments kernel ridge regression with an incrementally adaptive graph Laplacian regularizer. Starting with a purely spatial graph and updating it as we improve our image estimate makes the method more …
-
Deformable lung registration for pulmonary image analysis of MRI and CT scans
… optimisation framework, based on an image-adaptive graph structure, which enables a very efficient optimisation of large dense displacement spaces and deals well with sliding motion. The derived methods are applied to two different clinical applications in pulmonary image analysis: motion …
-
Deep Spatial-Temporal Learning in the Correlated Time Series
… factors. Second, we study more salient and adaptive spatial-temporal learning methods in the traffic forecasting scenario. We propose Adaptive Graph Convolutional Recurrent Network (AGCRN) to infer the spatial closeness from data automatically and capture fine-grained node-wise …
-
Image and Video-Based Autism Spectrum Disorder Detection via Deep Learning
… temporal information. In this study, we applied Graph Convolutional Network (GCN) to the 2D skeleton sequence to classify video recording the same action (brush teeth and wash face) as either from individuals with ASD or by peers without ASD. Furthermore, we adopted an adaptive graph mechanism …
-
A manifold learning approach to target detection in high-resolution hyperspectral imagery
… manifold that can be discretely modeled by a graph. The research presented here focuses on the use of graph theory and manifold learning in hyperspectral imagery. Early work explored various graph-building techniques with application to the background model of the Topological Anomaly Detection …
-
Advancing Geometric Deep Learning: From Fundamental Approaches to Drug Discovery Applications
… with geometrically structured data such as graphs, 3D geometries, and point clouds. In this dissertation, we particularly consider graph and geometric graph data and aim to contribute to the advancement of geometric deep learning by developing novel fundamental approaches and exploring drug …
-
Graph Learning for Urban Computing: Techniques and Applications
… feasible in practice. This dissertation develops graph learning frameworks for four urban computing tasks: sensor recovery, spatial generation, service boundary redesign, and infrastructure expansion. The first two are state-oriented, inferring or generating urban conditions within graph-based …
-
Lightweight Machine Learning with Brain Signals
Electroencephalography(EEG) signals are gaining popularity in Brain-Computer Interface(BCI) systems and neural engineering applications thanks to their portability and availability. Inevitably, the sensory electrodes on the entire scalp would collect signals irrelevant to the particular BCI task, …
-
Integration of Physical Knowledge into Machine-Learning Framework for Bias-Correction, Transport Modeling, and Equation Discovery of Surface Pollutant at Regional Scale
… is incorporated through data. AGATNet, an adaptive graph attention network with temporal convolutions, corrects PM2.5 biases from the Community Multiscale Air Quality model (CMAQ), a widely used chemical transport model (CTM), over a 72 forecast hours at 183 stations. Connectivity is …
-
Theoretical Analysis of Spectral Graph Neural Networks
Spectral Graph Neural Networks (GNNs) have demonstrated strong performance in graph node classification tasks, yet factors affecting their performance remains insufficiently understood. We provide theoretical analysis of factors affecting the performance of spectral GNNs in node classification …
-
St-Hybrid: Dynamic Graph Learning with Multi-Scale Spatio-Temporal Attention for Traffic Forecasting
… Systems, supporting route guidance, adaptive signal control, and incident response. Yet producing reliable predictions remains difficult because traffic is highly non-stationary. The relationships among roadway sensors shift during congestion, incidents, weather changes, or …
-
Deep Learning Frameworks for Anomaly Detection in Time Series and Graphs with Limited Labels
… on time series anomaly detection (TSAD) and graph anomaly detection (GAD). To overcome the issue of label scarcity, our initial work investigates unsupervised TSAD methods that extract meaningful patterns from abundant unlabeled data. Building on recent advances in contrastive learning from …
-
Adaptive Force-Directed Graph Drawing: Structure-Aware Methods and Reinforcement Learning-Based Parameter Control
Force-directed graph drawing provides a flexible approach to graph visualization, but layout quality can depend on graph structure and on how the layout process is configured during refinement. This thesis investigates two complementary approaches to adaptive force-directed drawing. The first …
-
A multi-agent distributed learning framework for the optimization of privacy and resilience in federated systems
… not as a static optimization protocol, but as an adaptive, structured, multi-agent process in which privacy, resilience, efficiency, and coordination are deeply intertwined. By treating participating agents as heterogeneous entities with distinct roles, influence, and constraints, and by …