Download PDFOpen PDF in browser

Exploring Graph Representation of Chorales

EasyChair Preprint 8872

15 pagesDate: September 24, 2022

Abstract

This work explores uncharted areas overlapping music, graph theory, and machine learning. An embedding representation of a node, in a weighted undirected graph G, is a representation that captures the meaning of nodes in an embedding space. In this work, 383 Bach chorales were compiled and represented as a graph representation. Two application cases were investigated in this paper (i) learning node embedding representation using Continuous Bag of Words (CBOW), skip-gram, and node2vec algorithms, and (ii) learning node labels from neighboring nodes based on a collective classification approach. The results of this exploratory study ascertain many salient features of the graph-based representation approach.

Keyphrases: Node embedding representation, collective classification, graph representation learning, node2vec

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@booklet{EasyChair:8872,
  author    = {Somnuk Phon-Amnuaisuk},
  title     = {Exploring Graph Representation of Chorales},
  howpublished = {EasyChair Preprint 8872},
  year      = {EasyChair, 2022}}
Download PDFOpen PDF in browser