Startseite
English
Erweiterte Suche
Durchblättern nach ...
Publikationen im Überblick
Ansprechpartner
Hilfe
Verlagsversion
 |
Open Access Gold (Paid Option) |
möglich sobald bei der ZB eingereicht worden ist.
On the Surprising Behaviour of \textttnode2vec.
In: (Proceedings of Machine Learning Research). 2022. 142-151 (Proceedings of Machine Learning Research ; 196)
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 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.
Weitere Metriken?
Zusatzinfos bearbeiten
[➜Einloggen]
Publikationstyp
Artikel: Konferenzbeitrag
Konferenztitel
Proceedings of Machine Learning Research
Quellenangaben
Band: 196,
Seiten: 142-151
Nichtpatentliteratur
Publikationen
Institut(e)
Institute of AI for Health (AIH)