</> Code with Papers by Syntology

Methods › General › Knowledge Distillation › Knowledge Distillation

Knowledge Distillation

3,071 papers tagged archive 2025-07-28

Introduced by Geoffrey Hinton et al. in Distilling the Knowledge in a Neural Network

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

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. Unfortunately, making predictions using a whole ensemble of models is cumbersome and may be too computationally expensive to allow deployment to a large number of users, especially if the individual models are large neural nets. Caruana and his collaborators have shown that it is possible to compress the knowledge in an ensemble into a single model which is much easier to deploy and we develop this approach further using a different compression technique. We achieve some surprising results on MNIST and we show that we can significantly improve the acoustic model of a heavily used commercial system by distilling the knowledge in an ensemble of models into a single model. We also introduce a new type of ensemble composed of one or more full models and many specialist models which learn to distinguish fine-grained classes that the full models confuse. Unlike a mixture of experts, these specialist models can be trained rapidly and in parallel. Source: Distilling the Knowledge in a Neural Network

PaperSource

Code snippet in the archive: a link on research.google (archive link, not checked and not linked: not a code host this site links to).

Papers archive 2025-07-28

30 shown of 3,071, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 1,024 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Knowledge Distillation3,039
Transfer Learning311
Model Compression253
Object Detection208
object-detection205
Image Classification202
Semantic Segmentation199
image-classification179
Language Modelling168
Language Modeling133
Federated Learning123
Representation Learning112
Data Augmentation111
Translation108
Segmentation105
Object99
Incremental Learning98
Quantization97
Contrastive Learning96
Continual Learning93

Usage over time archive 2025-07-28

Papers per year tagged with Knowledge Distillation: 2015 to 2025, peak 739 739 0 2015: 1 paper 2015 2016: 4 papers 2016 2017: 8 papers 2017 2018: 33 papers 2018 2019: 130 papers 2019 2020: 271 papers 2020 2021: 423 papers 2021 2022: 506 papers 2022 2023: 637 papers 2023 2024: 739 papers 2024 2025: 319 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (3,071 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Knowledge Distillation

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections