View Item 
        •   Utrecht University Student Theses Repository Home
        • UU Theses Repository
        • Theses
        • View Item
        •   Utrecht University Student Theses Repository Home
        • UU Theses Repository
        • Theses
        • View Item
        JavaScript is disabled for your browser. Some features of this site may not work without it.

        Browse

        All of UU Student Theses RepositoryBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

        Graph2DMatrix: Exploring Graph Neural Networks Ability to Visualize Multivariate Graphs with Reordered Matrices

        Thumbnail
        View/Open
        MbiThesis_Job_Heuvelmans_Final.pdf (68.84Mb)
        Publication date
        2022
        Author
        Heuvelmans, Job
        Metadata
        Show full item record
        Summary
        Previous research in graph embedding concentrates mainly on using embeddings for downstream machine learning tasks such as node classification, edge prediction and, to a lesser extent, on visualizing these embeddings for analytical examination. This study aims to determine whether high dimensional graph embeddings can be used to uncover structures in graphs, and visualize these in two dimensional matrices. We propose a framework that embeds a graph in high dimensions; calculates the pairwise distance matrix; reorders rows and columns in this matrix; and visualizes the original graph in a new matrix exploration tool. The goal of this framework is to supply individuals with high level knowledge on relational data. We test the framework by analyzing visual quality by feeding in basic pre-generated graphs. The random walk algorithms (e.g. DeepWalk, Walkets and attentionWalk) are able to accurately visualize 4 out of 6 of the canonical data patterns for a high level understanding of the data. Nevertheless, these basic graphs do not reflect complex relational data used in many real world applications, and therefore, we introduce two novel algorithms for embedding numerical node-attributed graphs (i.e. featPMI and featWalk). These algorithms are tested on a subset of the attributed Slovakian social network Pokec, in which both the algorithms show increasing information retention over the naive embedding of DeepWalk. Furthermore, featWalk is found to be preferred over featPMI with a clearer separation of patterns, and better feature preservation. Our findings indicate the potentiality of embeddings to generate valuable high level matrix visualizations.
        URI
        https://studenttheses.uu.nl/handle/20.500.12932/41646
        Collections
        • Theses

        Related items

        Showing items related by title, author, creator and subject.

        • Graph Challenge: Counting Triangles and Enumerating Trusses in Graphs 

          Sänger, E.M. (2019)
        • Graph Data Model: Storing temporal financial transaction data in a graph database. 

          Sinchico Arias, Amaru (2022)
        • 45 Anomaly detection with similarity graphs and active learning Building and storing static and dynamic similarity graphs with the help of a vector database 

          Kragting, Sebastiaan (2022)
          Fraudulent transactions of credit cards are a major problem for financial institutions and continues to grow along digital transformation. A conventional view states that fraudulent transactions are anomalies. A novel view ...
        Utrecht university logo