CliffSplit exposes at least 15% higher errors in cliff-heavy regions of QM9 while CliffLoss narrows the cliff-to-smooth error gap by up to 30% and improves overall MAE by 9.7% across several molecular tasks and backbones.
Dropout as a Bayesian approximation: Representing model uncertainty in deep learning
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Hybrid-Lift LSTM framework with actuarial anchoring outperforms Li-Lee by 17.4% in Sweden and 12.6% in West Germany on 2012-2020 out-of-sample longevity data while matching performance in linear regimes.
citing papers explorer
-
When Molecular Similarity Works: Property Cliffs Reveal Hidden Errors
CliffSplit exposes at least 15% higher errors in cliff-heavy regions of QM9 while CliffLoss narrows the cliff-to-smooth error gap by up to 30% and improves overall MAE by 9.7% across several molecular tasks and backbones.
-
Neural-Actuarial Longevity Forecasting: Anchoring LSTMs for Explainable Risk Management
Hybrid-Lift LSTM framework with actuarial anchoring outperforms Li-Lee by 17.4% in Sweden and 12.6% in West Germany on 2012-2020 out-of-sample longevity data while matching performance in linear regimes.