19 citations · 43 across the 9 of their papers we have counts for
9 papers
Federated Active Learning Under Extreme Non-IID and Global Class Imbalance
Chen-Chen Zong, Sheng-Jun Huang
Federated active learning (FAL) seeks to reduce annotation cost under privacy constraints, yet its effectiveness degrades in realistic settings with severe global class imbalance a…
Rethinking Epistemic and Aleatoric Uncertainty for Active Open-Set Annotation: An Energy-Based Approach
Chen-Chen Zong, Sheng-Jun Huang
Active learning (AL), which iteratively queries the most informative examples from a large pool of unlabeled candidates for model training, faces significant challenges in the pres…
Dual-Head Knowledge Distillation: Enhancing Logits Utilization with an Auxiliary Head
Penghui Yang, Chen-Chen Zong, Sheng-Jun Huang +2
Traditional knowledge distillation focuses on aligning the student's predicted probabilities with both ground-truth labels and the teacher's predicted probabilities. However, the t…
Dirichlet-Based Coarse-to-Fine Example Selection For Open-Set Annotation
Ye-Wen Wang, Chen-Chen Zong, Ming-Kun Xie +1
Active learning (AL) has achieved great success by selecting the most valuable examples from unlabeled data. However, they usually deteriorate in real scenarios where open-set nois…
CACL: Community-Aware Heterogeneous Graph Contrastive Learning for Social Media Bot Detection
Sirry Chen, Shuo Feng, Songsong Liang +3
Social media bot detection is increasingly crucial with the rise of social media platforms. Existing methods predominantly construct social networks as graph and utilize graph neur…
Bidirectional Uncertainty-Based Active Learning for Open Set Annotation
Chen-Chen Zong, Ye-Wen Wang, Kun-Peng Ning +2
Active learning (AL) in open set scenarios presents a novel challenge of identifying the most valuable examples in an unlabeled data pool that comprises data from both known and un…
Dirichlet-Based Prediction Calibration for Learning with Noisy Labels
Chen-Chen Zong, Ye-Wen Wang, Ming-Kun Xie +1
Learning with noisy labels can significantly hinder the generalization performance of deep neural networks (DNNs). Existing approaches address this issue through loss correction or…
Multi-Label Knowledge Distillation
Penghui Yang, Ming-Kun Xie, Chen-Chen Zong +4
Existing knowledge distillation methods typically work by imparting the knowledge of output logits or intermediate feature maps from the teacher network to the student network, whi…
Noise-Robust Bidirectional Learning with Dynamic Sample Reweighting
Chen-Chen Zong, Zheng-Tao Cao, Hong-Tao Guo +4
Deep neural networks trained with standard cross-entropy loss are more prone to memorize noisy labels, which degrades their performance. Negative learning using complementary label…