ePrints.FRI - University of Ljubljana, Faculty of Computer and Information Science

Vertex embeddings in linear space complexity

Vid Kocijan (2017) Vertex embeddings in linear space complexity. Prešeren awards for students.

Download (1092Kb)


    In order to predict the behaviour of networks with machine-learning algorithms, the vector representation of nodes in a low dimensional vector space is required. The current state-of-the-art algorithm for the calculation of node embeddings in vector space is Node2vec. Node2vec samples the network through the 2nd order random walks. Unfortunately, Node2vec has a high memory complexity due to the preprocessed probability-distribution tables. Due to high memory complexity, an average user is unable to use it for larger networks. In this thesis, we present a heuristic approach to the random walk simulation. The heuristic approach replaces probability tables with binary trees and guarantees linear time and space complexity, while retaining the quality of computed features. The heuristic approach requires from 6 up to 40 times less memory than Node2vec on tested datasets.

    Item Type: Thesis (Prešeren awards for students)
    Keywords: vertex embeddings, network, random walks
    Number of Pages: 30
    Language of Content: Slovenian
    Mentor / Comentors:
    Name and SurnameIDFunction
    prof. dr. Janez Demšar257Mentor
    doc. dr. Jure LeskovecComentor
    Link to COBISS: http://www.cobiss.si/scripts/cobiss?command=search&base=51012&select=(ID=1537656515)
    Institution: University of Ljubljana
    Department: Faculty of Computer and Information Science
    Item ID: 4019
    Date Deposited: 04 Dec 2017 12:25
    Last Modified: 05 Dec 2017 13:55
    URI: http://eprints.fri.uni-lj.si/id/eprint/4019

    Actions (login required)

    View Item