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 24 for “"graph attention"”.
-
Accelerating graph attention network inference on CPUs with layer fusion
Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2026-05-01
-
Graph Attention Mechanisms for Modeling Pathway-Level Importance from Gene Expression
… the integration of gene interactions through graph neural networks, and attentionbased hierarchical pooling from genes to pathways to latent sample representations. Across experimental trials, this architecture demonstrated stable training which had matched, if not improved, reconstruction and …
-
Understanding tumor cell plasticity in spatial transcriptomics with graph attention networks and walk-based pseudotime analysis
… be probed. We introduce PlastiNet, which uses a graphical attention-based network to create a spatial aware embedding. The utility of our approach is validated in model systems, specifically in the brain and colon, where it successfully identifies biologically relevant neighborhoods and maps …
-
Decentralized graph-based multi-agent reinforcement learning for traffic signal optimization
… This dissertation develops a decentralized graph-based multi-agent reinforcement learning (DGMARL) framework for adaptive traffic signal control. The framework advances the state of the art by (i) embedding operational constraints, including minimum/maximum green durations, pedestrian …
-
Hybrid AI-driven Approach to Context-Aware Inter-Slice Load Balancing for Cloud-Native Functions in 5G Networks
… interactions for intelligent capabilities. Graph neural networks (GNN) and spatio-temporal multi-head graph attention networks (SP-mGAT) are utilized to generate context-aware embeddings, clustering clients by traffic characteristics into priority labels. These labels feed multi-agent deep …
-
A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects
… subgoals for rigid-body manipulation and a graph-attention based neural network architecture for processing point-cloud inputs. We experimentally validate these choices using simulated and real-world experiments on the YuMi robot. Results demonstrate that our method can successfully …
-
From Protein Folds to Chromatin: Topological Data Analysis and Deep Learning at Multiple Scales
… extends the Computed Atlas of Surface Topography of Proteins by combining computational geometry, topological data analysis, and AI-based structure prediction to identify and quantify surface pockets, internal cavities, and cross channels across more than 183 million experimentally …
-
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 …
-
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 …
-
Controlling Behavior with Shared Knowledge
… by examining the impact of symbolic knowledge graph-based state representation and Hierarchical Graph Attention mechanism on the decision-making process of a reinforcement learning agent. The goal of this dissertation is to create AI-driven systems that are more coherent, controllable, and …
-
Graph Neural Networks for Health-Aware Food and Multi-Criteria Recommendation Systems
… Food Recommendation System with Dual Attention in Heterogeneous Graphs (HFRS-DA) and the Multiview Graph Dual Attention and Contrastive Learning for Multi-Criteria Recommender Systems (D-MGAC). The first framework, HFRS-DA, addresses the challenge of effectively integrating …
-
Learning NP-hard problems on networks using Geometric Deep Learning
… of Deep Learning to non-Euclidean domains like graphs, can aid the computation of NP-hard problems and learn heuristics from the data. Specifically, we define a framework, namely GDM, to learn how to solve the Network Dismantling and Link Building problems on the optimal solutions computed on …
-
Investigating Tree- and Graph-based Neural Networks for Natural Language Processing Applications
… within NLP applications. By leveraging tree- and graph-based neural networks, this study pioneers a holistic approach that augments language understanding and processing capabilities. Through the fusion of structural and semantic-driven insights, this work tries to explore various NLP applications …
-
Graph neural network approaches and real-time unsupervised learning for anomaly detection in vehicular networks
… vehicle interactions are modeled as dynamic graphs and evaluated using six Graph Neural Network (GNN) architectures: Graph Convolutional Network (GCN), Graph Attention Network (GAT), GraphSAGE, Temporal GCN (T-GCN), Gated Convolutional LSTM (GConvLSTM), and Gated Convolutional GRU (GConvGRU). …
-
Spatiotemporal Event Graphs for Dynamic Scene Understanding
… we present a deformable, spatiotemporal scene graph approach, consisting of three main building blocks: action tube detection, a 3D deformable RoI pooling layer designed for learning the flexible, deformable geometry of the constituent action tubes, and a scene graph constructed by considering …
-
Network-aware Multi-agent Reinforcement Learning for Adaptive Navigation of Vehicles in a Dynamic Road Network
… of the agent aggregated with a shared graph attention network (GAT) model, and (iii) routing policies learned by cooperating with other RL agents assigned to neighboring intersections. The vehicle follows the routing response from the router agents until it reaches its destination. …
-
Enabling AI Copilots for Engineering Design With Parametric, Graph, And Component Inputs
… detailed parametric specifications, assembly graphs, visual references, and textual descriptions. Despite growing interest in generative models for design ideation and exploration, state-of-the-art approaches struggle with incomplete inputs, lack of support for modalities other than text and …
-
GNN-Enhanced Hierarchical Federated Learning in Device-to-Device Networks
… these challenges, this thesis investigates a Graph Neural Networks (GNN)-enhanced hierarchical FL architecture in D2D networks, aiming to achieve efficient, adaptive, and scalable federated model training across distributed devices. To begin with, this thesis proposes an asynchronous …
Page 1 of 2