WSNET integrates weak-label classification and contrastive losses to learn node representations, outperforming baselines on weakly labeled graphs.
Data programming: Creating large training sets, quickly
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Weak Supervision for Real World Graphs
WSNET integrates weak-label classification and contrastive losses to learn node representations, outperforming baselines on weakly labeled graphs.