On the Surprising Behaviour of \textttnode2vec

Celia Hacker, Bastian Rieck
Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022, PMLR 196:142-151, 2022.

Abstract

Graph embedding techniques are a staple of modern graph learning research. When using embeddings for downstream tasks such as classification, information about their stability and robustness, i.e., their susceptibility to sources of noise, stochastic effects, or specific parameter choices, becomes increasingly important. As one of the most prominent graph embedding schemes, we focus on \texttt{node2vec} and analyse its embedding quality from multiple perspectives. Our findings indicate that embedding quality is unstable with respect to parameter choices, and we propose strategies to remedy this in practice.

Cite this Paper

BibTeX
@InProceedings{pmlr-v196-hacker22a, title = {On the Surprising Behaviour of node2vec}, author = {Hacker, Celia and Rieck, Bastian}, booktitle = {Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022}, pages = {142--151}, year = {2022}, editor = {Cloninger, Alexander and Doster, Timothy and Emerson, Tegan and Kaul, Manohar and Ktena, Ira and Kvinge, Henry and Miolane, Nina and Rieck, Bastian and Tymochko, Sarah and Wolf, Guy}, volume = {196}, series = {Proceedings of Machine Learning Research}, month = {25 Feb--22 Jul}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v196/hacker22a/hacker22a.pdf}, url = {https://proceedings.mlr.press/v196/hacker22a.html}, abstract = {Graph embedding techniques are a staple of modern graph learning research. When using embeddings for downstream tasks such as classification, information about their stability and robustness, i.e., their susceptibility to sources of noise, stochastic effects, or specific parameter choices, becomes increasingly important. As one of the most prominent graph embedding schemes, we focus on \texttt{node2vec} and analyse its embedding quality from multiple perspectives. Our findings indicate that embedding quality is unstable with respect to parameter choices, and we propose strategies to remedy this in practice.} }
Endnote
%0 Conference Paper %T On the Surprising Behaviour of \textttnode2vec %A Celia Hacker %A Bastian Rieck %B Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022 %C Proceedings of Machine Learning Research %D 2022 %E Alexander Cloninger %E Timothy Doster %E Tegan Emerson %E Manohar Kaul %E Ira Ktena %E Henry Kvinge %E Nina Miolane %E Bastian Rieck %E Sarah Tymochko %E Guy Wolf %F pmlr-v196-hacker22a %I PMLR %P 142--151 %U https://proceedings.mlr.press/v196/hacker22a.html %V 196 %X Graph embedding techniques are a staple of modern graph learning research. When using embeddings for downstream tasks such as classification, information about their stability and robustness, i.e., their susceptibility to sources of noise, stochastic effects, or specific parameter choices, becomes increasingly important. As one of the most prominent graph embedding schemes, we focus on \texttt{node2vec} and analyse its embedding quality from multiple perspectives. Our findings indicate that embedding quality is unstable with respect to parameter choices, and we propose strategies to remedy this in practice.
APA
Hacker, C. & Rieck, B.. (2022). On the Surprising Behaviour of \textttnode2vec. Proceedings of Topological, Algebraic, and Geometric Learning Workshops 2022, in Proceedings of Machine Learning Research 196:142-151 Available from https://proceedings.mlr.press/v196/hacker22a.html.

Related Material