8 papers
Online-BLS: An Accurate and Efficient Online Broad Learning System for Data Stream Classification
Chunyu Lei, Guang-Ze Chen, C. L. Philip Chen +1
The state-of-the-art online learning models generally conduct a single online gradient descent when a new sample arrives and thus suffer from suboptimal model weights. To this end,…
Reliable Multimodal Learning Via Multi-Level Adaptive DeConfusion
Tong Zhang, Shu Shen, C. L. Philip Chen
Multimodal learning enhances the performance of various machine learning tasks by leveraging complementary information across different modalities. However, existing methods often…
CRIA: A Cross-View Interaction and Instance-Adapted Pre-training Framework for Generalizable EEG Representations
Puchun Liu, C. L. Philip Chen, Yubin He +1
The difficulty of extracting deep features from EEG data and effectively integrating information from multiple views presents significant challenges for developing a generalizable…
Multi-QuAD: Multi-Level Quality-Adaptive Dynamic Network for Reliable Multimodal Classification
Shu Shen, C. L. Philip Chen, Tong Zhang
Multimodal machine learning has achieved remarkable progress in many scenarios, but its reliability is undermined by varying sample quality. This paper finds that existing reliable…
FACE: Few-shot Adapter with Cross-view Fusion for Cross-subject EEG Emotion Recognition
Haiqi Liu, C. L. Philip Chen, Tong Zhang
Cross-subject EEG emotion recognition is challenged by significant inter-subject variability and intricately entangled intra-subject variability. Existing works have primarily addr…
DEUCE: Dual-diversity Enhancement and Uncertainty-awareness for Cold-start Active Learning
Jiaxin Guo, C. L. Philip Chen, Shuzhen Li +1
Cold-start active learning (CSAL) selects valuable instances from an unlabeled dataset for manual annotation. It provides high-quality data at a low annotation cost for label-scarc…