paper-with-me

홈 › Papers

The Role of Teacher Calibration in Knowledge Distillation

2025-08-27 · Suyoung Kim, Seonguk Park, Junhoo Lee, Nojun Kwak arxiv

Knowledge Distillation (KD) has emerged as an effective model compression technique in deep learning, enabling the transfer of knowledge from a large teacher model to a compact student model. While KD has demonstrated significant success, it is not yet fully understood which factors contribute to improving the student's performance. In this paper, we reveal a strong correlation between the teacher's calibration error and the student's accuracy. Therefore, we claim that the calibration of the teacher model is an important factor for effective KD. Furthermore, we demonstrate that the performance of KD can be improved by simply employing a calibration method that reduces the teacher's calibration error. Our algorithm is versatile, demonstrating effectiveness across various tasks from classification to detection. Moreover, it can be easily integrated with existing state-of-the-art methods, consistently achieving superior performance.

📄 PDF Abstract BibTeX arXiv:2508.20224

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge DistillationModel Compression

Similar Papers 제목 키워드 기반

LoCa: Logit Calibration for Knowledge Distillation

2024-09-07 · Runming Yang, Taiqiang Wu, Yujiu Yang

Knowledge Distillation (KD), aiming to train a better student model by mimicking the teacher model, plays an important role in model compression. One typical way is to align the output logits. However, we find a common i…

image-classificationImage ClassificationKnowledge DistillationModel Compression+1

Hard Gate Knowledge Distillation -- Leverage Calibration for Robust and Reliable Language Model

2022-10-22 · Dongkyu Lee, Zhiliang Tian, Yingxiu Zhao, Ka Chun Cheung 외

In knowledge distillation, a student model is trained with supervisions from both knowledge from a teacher and observations drawn from a training data distribution. Knowledge of a teacher is considered a subject that hol…

Knowledge DistillationLanguage ModelingLanguage ModellingSentence+1

Rethinking the Knowledge Distillation From the Perspective of Model Calibration

2021-10-31 · Lehan Yang, Jincen Song

Recent years have witnessed dramatically improvements in the knowledge distillation, which can generate a compact student model for better efficiency while retaining the model effectiveness of the teacher model. Previous…

Knowledge Distillation

Faithful Knowledge Distillation

2023-06-07 · Tom A. Lamb, Rudy Brunel, Krishnamurthy Dj Dvijotham, M. Pawan Kumar 외

Knowledge distillation (KD) has received much attention due to its success in compressing networks to allow for their deployment in resource-constrained systems. While the problem of adversarial robustness has been studi…

Adversarial RobustnessKnowledge Distillation

Distillation Traps and Guards: A Calibration Knob for LLM Distillability

2026-04-21 · Weixiao Zhan, Yongcheng Jing, Leszek Rutkowski, Dacheng Tao arxiv

Knowledge distillation (KD) transfers capabilities from large language models (LLMs) to smaller students, yet it can fail unpredictably and also underpins model leakage risks. Our analysis revealed several distillation t…

Knowledge Distillation