HMFNet, a multi-feature graph network with harmonic feature mapping and a five-part loss, reports state-of-the-art F1 (0.4861) for molecular odor prediction on combined Leffingwell and GoodScents data.
Leffingwell & as- sociates
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
-
Multi-Hierarchical Fine-Grained Feature Mapping Driven by Feature Contribution for Molecular Odor Prediction
HMFNet, a multi-feature graph network with harmonic feature mapping and a five-part loss, reports state-of-the-art F1 (0.4861) for molecular odor prediction on combined Leffingwell and GoodScents data.