STAR combines set-function contrastive learning with optimal transport distribution calibration to perform graph few-shot node classification without any labels during meta-training.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Enhancing Unsupervised Graph Few-shot Learning via Set Functions and Optimal Transport
STAR combines set-function contrastive learning with optimal transport distribution calibration to perform graph few-shot node classification without any labels during meta-training.