7 papers
Mitigating Structural Overfitting: A Distribution-Aware Rectification Framework for Missing Feature Imputation
Yifan Song, Fenglin Yu, Yihong Luo +4
Incomplete node features are ubiquitous in real-world scenarios such as user profiling and cold-start recommendation, which severely hinders the practical deployment of graph learn…
Unsupervised Feature Selection via Robust Autoencoder and Adaptive Graph Learning
Feng Yu, MD Saifur Rahman Mazumder, Ying Su +1
Effective feature selection is essential for high-dimensional data analysis and machine learning. Unsupervised feature selection (UFS) aims to simultaneously cluster data and ident…
Multimodal Classification via Total Correlation Maximization
Feng Yu, Xiangyu Wu, Yang Yang +1
Multimodal learning integrates data from diverse sensors to effectively harness information from different modalities. However, recent studies reveal that joint learning often over…
Adaptive Debiasing Tsallis Entropy for Test-Time Adaptation
Xiangyu Wu, Dongming Jiang, Feng Yu +5
Mainstream Test-Time Adaptation (TTA) methods for adapting vision-language models, e.g., CLIP, typically rely on Shannon Entropy (SE) at test time to measure prediction uncertainty…
Text as Any-Modality for Zero-Shot Classification by Consistent Prompt Tuning
Xiangyu Wu, Feng Yu, Yang Yang +1
The integration of prompt tuning with multimodal learning has shown significant generalization abilities for various downstream tasks. Despite advancements, existing methods heavil…
Multi-Label Test-Time Adaptation with Bound Entropy Minimization
Xiangyu Wu, Feng Yu, Qing-Guo Chen +2
Mainstream test-time adaptation (TTA) techniques endeavor to mitigate distribution shifts via entropy minimization for multi-class classification, inherently increasing the probabi…