3 papers
cs.LG2024
Dual-Label Learning With Irregularly Present Labels
Mingqian Li, Qiao Han, Ruifeng Li +2
In multi-task learning, labels are often missing irregularly across samples, which can be fully labeled, partially labeled or unlabeled. The irregular label presence often appears…
cs.LG2024
BlockEcho: Retaining Long-Range Dependencies for Imputing Block-Wise Missing Data
Qiao Han, Mingqian Li, Yao Yang +1
Block-wise missing data poses significant challenges in real-world data imputation tasks. Compared to scattered missing data, block-wise gaps exacerbate adverse effects on subseque…
cs.LG2024
Enhancing the "Immunity" of Mixture-of-Experts Networks for Adversarial Defense
Qiao Han, yong huang, xinling Guo +3
Recent studies have revealed the vulnerability of Deep Neural Networks (DNNs) to adversarial examples, which can easily fool DNNs into making incorrect predictions. To mitigate thi…