Modified LCEN for classification selects sparse features and achieves high F1 and MCC scores, while the diffMCC loss outperforms weighted cross-entropy by 4.9% F1 and 8.5% MCC on average across experiments.
Random decision forests , year=
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Improving Performance in Classification Tasks with LCEN and the Weighted Focal Differentiable MCC Loss
Modified LCEN for classification selects sparse features and achieves high F1 and MCC scores, while the diffMCC loss outperforms weighted cross-entropy by 4.9% F1 and 8.5% MCC on average across experiments.