2021/12/30 by Hailin Zhang, Defang Chen, Zhang, Hailin +3 · 4 citations
Computer Science · #Artificial Intelligence (cs.AI) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and Data Classification #Online Learning and Analytics
paper · pdf · doi:10.48550/arxiv.2201.00007
openalex publication_date 2021/12/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Knowledge distillation is initially introduced to utilize additional supervision from a single teacher model for the student model training. To boost the student performance, some recent variants attempt to exploit diverse knowledge sources from multiple teachers. However, existing studies mainly integrate knowledge from diverse sources by averaging over multiple teacher predictions or combining them using other various label-free strategies, which may mislead student in the presence of low-quality teacher predictions. To tackle this problem, we propose Confidence-Aware Multi-teacher Knowledge Distillation (CA-MKD), which adaptively assigns sample-wise reliability for each teacher prediction with the help of ground-truth labels, with those teacher predictions close to one-hot labels assigned large weights. Besides, CA-MKD incorporates intermediate layers to stable the knowledge transfer process. Extensive experiments show that our CA-MKD consistently outperforms all compared state-of-the-art methods across various teacher-student architectures.