2022
DOI: 10.48550/arxiv.2208.02810
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Analyzing Data-Centric Properties for Graph Contrastive Learning

Abstract: Recent analyses of self-supervised learning (SSL) find the following data-centric properties to be critical for learning good representations: invariance to taskirrelevant semantics, separability of classes in some latent space, and recoverability of labels from augmented samples. However, given their discrete, non-Euclidean nature, graph datasets and graph SSL methods are unlikely to satisfy these properties. This raises the question: how do graph SSL methods, such as contrastive learning (CL), work well? To … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
0
0

Publication Types

Select...

Relationship

0
0

Authors

Journals

citations
Cited by 0 publications
references
References 16 publications
0
0
0
Order By: Relevance

No citations

Set email alert for when this publication receives citations?