Differences

This shows you the differences between two versions of the page.

--- ml:knowledge_distillation [2021/03/11 10:27] – jmflanig
+++ ml:knowledge_distillation [2025/05/12 08:11] (current) – [Overviews] jmflanig
@@ Line 1: / Line 1: @@
 ====== Knowledge Distillation ======
+Various papers related to distillation.  From [[https://arxiv.org/pdf/2006.11316.pdf|Iandola 2020]]: "While the term 'knowledge distillation' was coined by Hinton et al. 2015 to describe a specific method and equation, the term 'distillation' is now used in reference to a diverse range of approaches where a 'student' network is trained to replicate a 'teacher' network."
+===== Overviews =====
+  * Section 4.2.2 of [[https://arxiv.org/pdf/2006.11316.pdf|Iandola 2020]]
+  * [[https://arxiv.org/pdf/2402.13116|Xu et al 2024 - A Survey on Knowledge Distillation of Large Language Models]]
 ===== Papers =====
-  * [[https://arxiv.org/pdf/1503.02531.pdf|Hinton et al 2015 - Distilling the Knowledge in a Neural Network]] (The paper that introduced knowledge distillation.)
+  * [[https://arxiv.org/pdf/1503.02531.pdf|Hinton et al 2015 - Distilling the Knowledge in a Neural Network]] (The paper that introduced **knowledge distillation**.)
+  * [[https://arxiv.org/pdf/1606.07947.pdf|Kim & Rush 2016 - Sequence-Level Knowledge Distillation]] First paper applying knowledge distillation to seq2seq models.
+  * Multi-step KD: [[https://arxiv.org/pdf/1902.03393.pdf|Mirzadeh et al 2019 - Improved Knowledge Distillation via Teacher Assistant]]
+  * [[https://arxiv.org/pdf/2104.06457.pdf|Inaguma et al 2021 - Source and Target Bidirectional Knowledge Distillation for End-to-end Speech Translation]]
+===== Related Pages =====
+  * [[Ensembling]]
+  * [[Model Compression]]