A node-weighted loss combining inverse-frequency weighting and ensemble-uncertainty focal terms improves recall of rare classes in hierarchical multi-label models by up to ~5x.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Improving Detection of Rare Nodes in Hierarchical Multi-Label Learning
A node-weighted loss combining inverse-frequency weighting and ensemble-uncertainty focal terms improves recall of rare classes in hierarchical multi-label models by up to ~5x.