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 8 of 8 for “"Full graph"”.

  1. Scaling Parallel Full-graph GNN Training to Thousands of GPUs

    Graph neural networks have emerged as a potent class of neural networks capableof leveraging the connectivity and structure of real-world graphs to learn intricate properties and relationships between nodes. Many real-world graphs exceed the memory capacity of a GPU due to their sheer size, and …

    maryland Repository record for Scaling Parallel Full-graph GNN Training to Thousands of GPUs (opens in a new tab)

  2. Graphs and Noncommutative Koszul Algebras

    … by relating a certain class of directed graphs to noncommutative Koszul algebras. The directed graphs in this class are called full graphs and are defined by a set of criteria on the edges. The structural properties of full graphs are studied as they relate to the edge criteria. A method …

    vt Repository record for Graphs and Noncommutative Koszul Algebras (opens in a new tab)

  3. Multi-Agent Narrative Experience Management as Story Graph Pruning

    … intelligent interactive narratives through story graph representation and pruning. The space of all stories can be represented as a story graph where nodes are states and edges are actions. By shaping the domain as a story graph, experience manager decisions can be made by pruning edges. Starting …

    uno Repository record for Multi-Agent Narrative Experience Management as Story Graph Pruning (opens in a new tab)

  4. Maršrutų optimizavimo algoritmai /

    … problem of optimal route creation is still not fully resolved in an increasingly important transport field, and there is a need to improve existing route optimization algorithms. Therefore, this paper seeks to overview the main algorithms of route optimization, analyze them, test and compare them …

    vilnius Repository record for Maršrutų optimizavimo algoritmai / (opens in a new tab)

  5. Bayesian Model Selection for Discrete Graphical Models

    Graphical models allow for easy interpretation and representation of complex distributions. There is an expanding interest in model selection problems for high-dimensional graphical models, particularly when the number of variables increases with the sample size. A popular model selection tool is …

    york Repository record for Bayesian Model Selection for Discrete Graphical Models (opens in a new tab)

  6. Η αστική εξάπλωση μέσω συμβολομετρίας

    … Pleiades Tri-stereo images for accurate topography subtraction from the interferograms. The results highlight the potential of this research and offer an important point of view on the building activity trend in time which is very crucial information for urban studies and the rapidly …

    greece Repository record for Η αστική εξάπλωση μέσω συμβολομετρίας (opens in a new tab)

  7. Information extraction from digital social trace data with applications to social media and scholarly communication data

    … This identification allows us to utilize the graph structure of the data (e.g., user connected to a tweet, author connected to a paper, author connected to authors, etc.) for developing new information extraction tasks. The thesis focuses on information extraction from DSTD, first, using only …

    uiuc Repository record for Information extraction from digital social trace data with applications to social media and scholarly communication data (opens in a new tab)

  8. Stochastic Analysis on Graphons

    … Homomorphism densities of finite simple graphs offer a rich class of examples of invariant functions that prominently feature in several areas of mathematics. In this thesis, we study two natural classes of interrelated problems. The first problem concerns the optimization of invariant …

    washington Repository record for Stochastic Analysis on Graphons (opens in a new tab)