Original paper

Negative sampling strategies for contrastive self-supervised learning of graph representations

Volume: 190, Pages: 108310 - 108310
Published: Jan 1, 2022
Abstract
Contrastive learning has become a successful approach for learning powerful text and image representations in a self-supervised manner. Contrastive frameworks learn to distinguish between representations coming from augmentations of the same data point (positive pairs) and those of other (negative) examples. Recent studies aim at extending methods from contrastive learning to graph data. In this work, we propose a general framework for learning...
Paper Details
Title
Negative sampling strategies for contrastive self-supervised learning of graph representations
Published Date
Jan 1, 2022
Volume
190
Pages
108310 - 108310
Citation AnalysisPro
  • Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
  • Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.