iN2V extends node2vec embeddings to unseen nodes via iterative neighbor averaging with train-time modifications, improving node classification by about 1 point on average over Feature Propagation.
Translating embeddings for modeling multi-relational data
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
-
iN2V: Bringing Transductive Node Embeddings to Inductive Graphs
iN2V extends node2vec embeddings to unseen nodes via iterative neighbor averaging with train-time modifications, improving node classification by about 1 point on average over Feature Propagation.