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 128 for “"Graph representations"”.

  1. Graph representations using stars, trees, intervals and boxes

    We introduce star number (tree number) of a graph G, which is the minimum t such that G is the intersection graph of unions of t substars (subtrees) of a host tree. We characterize the graphs with star number 1 and prove that a planar graph has star number at most 3. We study bounds on these two …

    uiuc Repository record for Graph representations using stars, trees, intervals and boxes (opens in a new tab)

  2. Wavelet scattering and graph representations for atomic structures

    … wavelet scattering approach and apply them to a graph based model to generate a rich representation. This requires developing novel ways to encode the bond angle and multiscale aspects of the atomic structure for the graph. We test this model on a data set of quantum molecular dynamics …

    msu Repository record for Wavelet scattering and graph representations for atomic structures (opens in a new tab)

  3. Map conflation via knowledge graph representations of digital maps

    … we design MINOR (Map Conflation via Knowledge Graph Representation), a machine-learning approach consisting of three parts: (1) Knowledge Graph Construction: where each GDB is represented by a knowledge graph (2) Map Matching: where we use a knowledge graph alignment method as well as a …

    ubc Repository record for Map conflation via knowledge graph representations of digital maps (opens in a new tab) Download PDF for Map conflation via knowledge graph representations of digital maps (opens in a new tab)

  4. Learning Flexible Graph Representations for 3D Human Pose Estimation

    … joint articulation, and depth ambiguities. Graph Convolutional Network (GCN)-based methods have proven effective by modeling the human skeleton as a graph of joints and bones. However, standard GCNs are limited by one-hop neighbor aggregation, as well as spectral bias, which emphasizes …

    concordia Download PDF for Learning Flexible Graph Representations for 3D Human Pose Estimation (opens in a new tab)

  5. Using Multi-Relational Embeddings as Knowledge Graph Representations for Robotics Applications

    … knowledge, which can be modeled as a knowledge graph of interrelated facts that define whether a relationship exists between two entities. Semantic reasoning about domain knowledge using knowledge graph representations has improved the robustness and usability of end user robots by enabling more …

    gatech Repository record for Using Multi-Relational Embeddings as Knowledge Graph Representations for Robotics Applications (opens in a new tab)

  6. 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

    uiuc Repository record for Forecasting without sequences: graph representations for dynamic systems in finance and beyond using GNNs (opens in a new tab)

  7. Unified logic maze generation: combining state graph representations and local search for diverse puzzle design

    Several logic mazes and their state graph representations are defined with the goal of generating additional instances of each maze. As Local Search proved to be an effective mad maze generation method, we focused on defining an objective function that considers maze characteristics. By …

    colo-mines Repository record for Unified logic maze generation: combining state graph representations and local search for diverse puzzle design (opens in a new tab)

  8. Representation Learning For Large-scale Graphs

    Graphs are widely used to model object relationships in real world applications such as biology, neuroscience, and communication networks. Traditional graph analysis tools focus on extracting key graph patterns to characterize graphs which are further used in the downstream tasks such as …

    maryland Repository record for Representation Learning For Large-scale Graphs (opens in a new tab)

  9. Immersions with local Lipschitz representation

    … for such kind of immersions, using local graph representations over the affine tangent space. As a corollary we show a convergence result for measures defined by such immersions. Inspired by these results, in the second part we like to take immersions with uniform graph representations as …

    freiburg-diss Repository record for Immersions with local Lipschitz representation (opens in a new tab)

  10. Large grain data flow graph construction and restructuring utilizing the ECOS Workstation System.

    … of trigger queues (dependency arcs) into the graphs to control execution. I utilized the EMSP Common Operational Software (ECOS) Workstation to execute graph representations of specific applications used by the U.S. Navy in the Anti-Submarine Warfare (ASW) arena. A complete description of the …

    nps Repository record for Large grain data flow graph construction and restructuring utilizing the ECOS Workstation System. (opens in a new tab)

  11. Delta-System Methods in Contemporary Graph Theory

    Our final problem is one in graph representations. We develop a lemma on traces of hypergraphs, extending results of Balogh and Bollobas. We then use this lemma, along with probabilistic methods, to show that for every positive integer k, almost every graph has no …

    uiuc Repository record for Delta-System Methods in Contemporary Graph Theory (opens in a new tab)

  12. Log-to-graph methodology for malicious activities detection in automated cloud infrastructure

    … dependencies across services, and many graph-based methods rely on extensive labelled data or offer limited interpretability. This thesis presents an end-to-end semi-supervised methodology for detecting malicious activities in automated cloud infrastructures using graph representations …

    soton Repository record for Log-to-graph methodology for malicious activities detection in automated cloud infrastructure (opens in a new tab) Download PDF for Log-to-graph methodology for malicious activities detection in automated cloud infrastructure (opens in a new tab)

  13. Steps Forward in Approximate Computational Inference

    … modelling computational inference problems with graphs, and how the graph representations can be used in the algorithmic level. The graph representations are used in learning Bayesian networks with more granular dependency structures. Finally, graphs are used for effective modelling of the ABC …

    aalto Repository record for Steps Forward in Approximate Computational Inference (opens in a new tab)

  14. Data-centric methods for optimization and pattern discovery in networked systems

    … on identifying design patterns in architecture graph representations of operational systems. Design patterns have been well documented and researched in software systems as a valuable design tool since the nineties. However, their usage has not been significantly expanded beyond software …

    uiuc Repository record for Data-centric methods for optimization and pattern discovery in networked systems (opens in a new tab)

  15. Reasoning about quantities in natural language

    … reasoning. On this front, we first propose graph representations called ""unit dependency graphs'', and show that these graph representations can be used to effectively incorporate dimensional analysis knowledge in quantitative reasoning. Next, we develop a general framework to incorporate …

    uiuc Repository record for Reasoning about quantities in natural language (opens in a new tab)

  16. Graph-Theoretic Techniques for Web Content Mining

    … data mining on web documents which utilize graph representations of document content. Graphs are more robust than typical vector representations as they can model structural information that is usually lost when converting the original web document content to a vector representation. For …

    usf Repository record for Graph-Theoretic Techniques for Web Content Mining (opens in a new tab)

  17. A Graph-based Approach for Semantic Data Mining

    … model to describe information resources as a graph. On the other hand, there has been a surge of interest in tackling data mining problems where objects of interest can be best described as a graph of interrelated nodes. I notice that the interface between domain knowledge and data mining can …

    oregon Repository record for A Graph-based Approach for Semantic Data Mining (opens in a new tab)

  18. Graph based techniques for measurement of intranet dynamics

    This thesis develops a number of graph-based techniques that are capable of measuring the dynamic behaviour of a network and discusses their application in network management. By representing a computer network as a time series of uniquely labelled graphs, it is possible to measure the degree of …

    adelaide Repository record for Graph based techniques for measurement of intranet dynamics (opens in a new tab)

Page 1 of 7