Graph node embeddings are learned by repeatedly adding noisy neighbor embeddings weighted by transition probabilities, with variance annealed over iterations, and tested on link prediction, reconstruction, and retail recommendations.
Spread of information through a population with socio- structural bias: I
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Hebbian Graph Embeddings
Graph node embeddings are learned by repeatedly adding noisy neighbor embeddings weighted by transition probabilities, with variance annealed over iterations, and tested on link prediction, reconstruction, and retail recommendations.