Prototypical networks are more robust than GCNs when active few-shot vertex classification is run from a completely unlabeled graph without a class oracle.
Siamese neural networks for one-shot image recognition,
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
-
Active Few-Shot Learning for Vertex Classification Starting from an Unlabeled Dataset
Prototypical networks are more robust than GCNs when active few-shot vertex classification is run from a completely unlabeled graph without a class oracle.