# FLHonker/Awesome-Knowledge-Distillation

Awesome Knowledge-Distillation. 分类整理的知识蒸馏paper(2014-2021)。

Repository: https://github.com/FLHonker/Awesome-Knowledge-Distillation
Canonical: https://ross.abutalabs.com/products/flhonker-awesome-knowledge-distillation
License Family: other
Topics: kd, knowldge-distillation, distillation, deep-learning, transfer-learning, model-compression
Last push: 2023-05-30T09:48:48+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2512, "days_push": 1191, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2685, forks 333 (observed 2026-08-28T04:07:10.186483+00:00)

## What it is
A curated awesome-list of knowledge distillation papers (2014-2021), organized by categories such as knowledge forms, KD+GAN, data-free KD, and applications. It also links to distiller tools and related model compression techniques like pruning and quantization.

## Use cases
- find papers on knowledge distillation
- learn about model compression techniques
- survey research on distilling knowledge from logits and intermediate layers
- find data-free knowledge distillation papers
- discover tools for distilling neural networks
- research teacher-student network training

## When to choose
- you need a categorized bibliography of KD research
- you are starting research in model compression or distillation
- you want to survey KD applications in NLP or recommender systems

## When to avoid
- you need runnable distillation code rather than paper references
- you need papers published after 2021
- you need a maintained software library

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, deep-learning, developer-tools
- domain: deep-learning, machine-learning, awesome-lists, tutorials
- platform: cross-platform
- tags: awesome-list, knowledge-distillation, model-compression, papers, transfer-learning, curated-list

## Member repositories
- FLHonker/Awesome-Knowledge-Distillation (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:10.186483+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:17:48.916631+00:00, confidence not recorded.
  - readme: https://github.com/FLHonker/Awesome-Knowledge-Distillation (fetched 2026-08-28T04:07:10.186483+00:00, sha 1c4639634184)
- Data as of 2026-08-30T08:39:29.467469+00:00.