2 papers
cs.LG2026
MAFS: Multi-head Attention Feature Selection for High-Dimensional Data via Deep Fusion of Filter Methods
Xiaoyan Sun, Qingyu Meng, Yalu Wen
Feature selection is essential for high-dimensional biomedical data, enabling stronger predictive performance, reduced computational cost, and improved interpretability in precisio…
cs.CL2025
Batch Aggregation: An Approach to Enhance Text Classification with Correlated Augmented Data
Charco Hui, Yalu Wen
Natural language processing models often face challenges due to limited labeled data, especially in domain specific areas, e.g., clinical trials. To overcome this, text augmentatio…