Dynamic Temperature Scheduler for Knowledge Distillation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917086380425216 |
|---|---|
| author | Islam, Sibgat Ul Ahad, Jawad Ibn Rahman, Fuad Amin, Mohammad Ruhul Mohammed, Nabeel Rahman, Shafin |
| author_facet | Islam, Sibgat Ul Ahad, Jawad Ibn Rahman, Fuad Amin, Mohammad Ruhul Mohammed, Nabeel Rahman, Shafin |
| contents | Knowledge Distillation (KD) trains a smaller student model using a large, pre-trained teacher model, with temperature as a key hyperparameter controlling the softness of output probabilities. Traditional methods use a fixed temperature throughout training, which is suboptimal. Moreover, architectural differences between teacher and student often result in mismatched logit magnitudes. We demonstrate that students benefit from softer probabilities early in training but require sharper probabilities in later stages. We introduce Dynamic Temperature Scheduler (DTS), which adjusts temperature dynamically based on the cross-entropy loss gap between teacher and student. To our knowledge, this is the first temperature scheduling method that adapts based on the divergence between teacher and student distributions. Our method integrates seamlessly with existing KD frameworks. We validate DTS across multiple KD strategies on vision (CIFAR-100, Tiny-ImageNet) and NLP tasks (GLUE, Dolly, SelfIns, UnNI, S-NI), consistently outperforming static-temperature baselines. Code is available at https://github.com/Sibgat-Ul/DTS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_13767 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Dynamic Temperature Scheduler for Knowledge Distillation Islam, Sibgat Ul Ahad, Jawad Ibn Rahman, Fuad Amin, Mohammad Ruhul Mohammed, Nabeel Rahman, Shafin Machine Learning Artificial Intelligence Knowledge Distillation (KD) trains a smaller student model using a large, pre-trained teacher model, with temperature as a key hyperparameter controlling the softness of output probabilities. Traditional methods use a fixed temperature throughout training, which is suboptimal. Moreover, architectural differences between teacher and student often result in mismatched logit magnitudes. We demonstrate that students benefit from softer probabilities early in training but require sharper probabilities in later stages. We introduce Dynamic Temperature Scheduler (DTS), which adjusts temperature dynamically based on the cross-entropy loss gap between teacher and student. To our knowledge, this is the first temperature scheduling method that adapts based on the divergence between teacher and student distributions. Our method integrates seamlessly with existing KD frameworks. We validate DTS across multiple KD strategies on vision (CIFAR-100, Tiny-ImageNet) and NLP tasks (GLUE, Dolly, SelfIns, UnNI, S-NI), consistently outperforming static-temperature baselines. Code is available at https://github.com/Sibgat-Ul/DTS. |
| title | Dynamic Temperature Scheduler for Knowledge Distillation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2511.13767 |