@inproceedings{d8df4c60914746b897c1073f9bc2e5da,
title = "Wire before You Walk",
abstract = "Node embeddings aim to associate a vector to every vertex of a graph which can then be used for downstream tasks such as clustering, classification, or link prediction. Many popular node embeddings such as node2vec and DeepWalk are based upon counting which nodes frequently co-occur in random walks of the graph. In this paper, we show that the performance of such algorithms can be improved by rewiring the edges of the graph through a variety of network indices before running DeepWalk. These rewirings effectively give the random walker an inductive bias and increase the accuracy of a logistic regression classifier applied to the node embedding on several benchmark data sets.",
keywords = "learning on graphs, node embeddings, skip-gram methods",
author = "Tesfa Asmara and Dhananjay Bhaskar and Ian Adelstein and Smita Krishnaswamy and Michael Perlmutter",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 57th Asilomar Conference on Signals, Systems and Computers, ACSSC 2023 ; Conference date: 29-10-2023 Through 01-11-2023",
year = "2023",
doi = "10.1109/IEEECONF59524.2023.10477089",
language = "English",
series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",
publisher = "IEEE Computer Society",
pages = "714--716",
editor = "Matthews, {Michael B.}",
booktitle = "Conference Record of the 57th Asilomar Conference on Signals, Systems and Computers, ACSSC 2023",
}