2 papers
cs.LG2026
Importance Scoring of Transformer Attention Heads in Learning Tabular Data
Ahmad Jad Allah, Kazi F. Akhter, Md. Kamrozzaman Bhuiyan +1
Computationally demanding and opaque deep learning models can be better understood and optimized by analyzing how they transform data. While deep transformers have been widely stud…
cs.LG2026
Ensemble of Unsupervised Deep Learning for Clustering Imbalanced Tabular Data
Pulock Das, Yina Hou, Md. Kamrozzaman Bhuiyan +1
Data imbalance poses a major challenge in supervised classification, where the majority-class bias contributes to false negatives and overestimates classification accuracy. Unsuper…