UAGA aligns two graph embedding spaces via adversarial training in a fully unsupervised setting, with an incremental extension iUAGA that uses discovered pseudo-anchors to refine both embeddings and alignments.
node2vec: Scalable feature learning for networks,
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2019 2verdicts
UNVERDICTED 2representative citing papers
Proposes regional uncertainty and page-rank extended query selection for active learning on graphs, claiming superiority over standard methods at different labeling densities.
citing papers explorer
-
Unsupervised Adversarial Graph Alignment with Graph Embedding
UAGA aligns two graph embedding spaces via adversarial training in a fully unsupervised setting, with an incremental extension iUAGA that uses discovered pseudo-anchors to refine both embeddings and alignments.
-
Regional based query in graph active learning
Proposes regional uncertainty and page-rank extended query selection for active learning on graphs, claiming superiority over standard methods at different labeling densities.