Enhancing Aboveground Biomass Prediction through Integration of the SCDR Paradigm into the U-Like Hierarchical Residual Fusion Model

R Zhang, J Peng, H Chen, H Peng, Y Wang, P Jiang - Sensors, 2024 - mdpi.com
Deep learning methodologies employed for biomass prediction often neglect the intricate
relationships between labels and samples, resulting in suboptimal predictive performance …

IM-Context: In-Context Learning for Imbalanced Regression Tasks

I Nejjar, F Ahmed, O Fink - arXiv preprint arXiv:2405.18202, 2024 - arxiv.org
Regression models often fail to generalize effectively in regions characterized by highly
imbalanced label distributions. Previous methods for deep imbalanced regression rely on …

Function Aligned Regression: A Method Explicitly Learns Functional Derivatives from Data

D Zhu, L Jerby-Arnon - arXiv preprint arXiv:2402.06104, 2024 - arxiv.org
Regression is a fundamental task in machine learning that has garnered extensive attention
over the past decades. The conventional approach for regression involves employing loss …