paper-with-me

홈 › Papers

Confidence-Aware Multi-Teacher Knowledge Distillation

2021-12-30 · Hailin Zhang, Defang Chen, Can Wang

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.

📄 PDF Abstract BibTeX arXiv:2201.00007

Code (1)

Rorozhl/CA-MKD 공식 구현 pytorch

Tasks

Knowledge DistillationTransfer Learning

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Uncertainty-Aware Dual-Student Knowledge Distillation for Efficient Image Classification

2025-11-24 · Aakash Gore, Anoushka Dey, Aryan Mishra arxiv

Knowledge distillation has emerged as a powerful technique for model compression, enabling the transfer of knowledge from large teacher networks to compact student models. However, traditional knowledge distillation meth…

Knowledge DistillationImage ClassificationModel Compression

H-OPD: Confidence Aware Heterogeneous Multi-Teacher Multimodal On-policy Distillation

2026-07-01 · Qixiang Yin, Huanjin Yao, Yuchen Cai, Jianghao Chen 외 arxiv

On-policy distillation (OPD) has recently emerged as an effective post-training paradigm by providing supervision on student-generated trajectories. However, existing OPD methods for multimodal reasoning usually rely on …

Multimodal ReasoningVisual Grounding

Revisiting Cross-Architecture Distillation: Adaptive Dual-Teacher Transfer for Lightweight Video Models

2025-11-12 · Ying Peng, Hongsen Ye, Changxin Huang, Xiping Hu 외 arxiv

Vision Transformers (ViTs) have achieved strong performance in video action recognition, but their high computational cost limits their practicality. Lightweight CNNs are more efficient but suffer from accuracy gaps. Cro…

Knowledge DistillationAction Recognition

Confidence-aware Self-Semantic Distillation on Knowledge Graph Embedding

2022-06-07 · Yichen Liu, Jiawei Chen, Defang Chen, Zhehui Zhou 외

Knowledge Graph Embedding (KGE), which projects entities and relations into continuous vector spaces, has garnered significant attention. Although high-dimensional KGE methods offer better performance, they come at the e…

Graph EmbeddingKnowledge DistillationKnowledge Graph EmbeddingKnowledge Graphs+3

Distillation Matters: Empowering Sequential Recommenders to Match the Performance of Large Language Model

2024-05-01 · Yu Cui, Feng Liu, Pengbo Wang, Bohao Wang 외

Owing to their powerful semantic reasoning capabilities, Large Language Models (LLMs) have been effectively utilized as recommenders, achieving impressive performance. However, the high inference latency of LLMs signific…

Knowledge DistillationLanguage ModelingLanguage ModellingLarge Language Model