# HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers

arXiv: https://arxiv.org/abs/2302.09632 · HTML: https://mlsanity.com/paper/2302.09632/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge distillation for LLMs, one of 12 directions in Knowledge distillation.
- Builds on 54 of its 71 references that are in the map.
- First posted on arXiv 19 Feb 2023.

## Placed in

- Knowledge distillation / [Knowledge distillation for LLMs](https://mlsanity.com/distill/knowledge-distillation-for-llms/)

## Builds on (most cited first, 30 of 54)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference](https://mlsanity.com/paper/1704.05426/) (2017)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Learning both Weights and Connections for Efficient Neural Networks](https://mlsanity.com/paper/1506.02626/) (2015)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Know What You Don't Know: Unanswerable Questions for SQuAD](https://mlsanity.com/paper/1806.03822/) (2018)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing](https://mlsanity.com/paper/2111.09543/) (2021)
- [TinyBERT: Distilling BERT for Natural Language Understanding](https://mlsanity.com/paper/1909.10351/) (2019)
- [Aligning Books and Movies: Towards Story-like Visual Explanations by Watching Movies and Reading Books](https://mlsanity.com/paper/1506.06724/) (2015)
- [SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation](https://mlsanity.com/paper/1708.00055/) (2017)
- [Neural Network Acceptability Judgments](https://mlsanity.com/paper/1805.12471/) (2018)
- [Are Sixteen Heads Really Better than One?](https://mlsanity.com/paper/1905.10650/) (2019)
- [SNIP: Single-shot Network Pruning based on Connection Sensitivity](https://mlsanity.com/paper/1810.02340/) (2018)
- [To prune, or not to prune: exploring the efficacy of pruning for model compression](https://mlsanity.com/paper/1710.01878/) (2017)
- [Improved Knowledge Distillation via Teacher Assistant](https://mlsanity.com/paper/1902.03393/) (2019)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [Patient Knowledge Distillation for BERT Model Compression](https://mlsanity.com/paper/1908.09355/) (2019)
- [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://mlsanity.com/paper/2004.02984/) (2020)
- [Movement Pruning: Adaptive Sparsity by Fine-Tuning](https://mlsanity.com/paper/2005.07683/) (2020)
- [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019)
- [DynaBERT: Dynamic BERT with Adaptive Width and Depth](https://mlsanity.com/paper/2004.04037/) (2020)

## Built on by (most cited first, 25 of 25)

- [LLM-Pruner: On the Structural Pruning of Large Language Models](https://mlsanity.com/paper/2305.11627/) (2023)
- [LLM Inference Unveiled: Survey and Roofline Model Insights](https://mlsanity.com/paper/2402.16363/) (2024)
- [Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models](https://mlsanity.com/paper/2408.10189/) (2024)
- [Model Compression and Efficient Inference for Large Language Models: A Survey](https://mlsanity.com/paper/2402.09748/) (2024)
- [Survey on Knowledge Distillation for Large Language Models: Methods, Evaluation, and Application](https://mlsanity.com/paper/2407.01885/) (2024)
- [A Survey of Techniques for Optimizing Transformer Inference](https://mlsanity.com/paper/2307.07982/) (2023)
- [Wanda++: Pruning Large Language Models via Regional Gradients](https://mlsanity.com/paper/2503.04992/) (2025)
- [Grounding Foundation Models through Federated Transfer Learning: A General Framework](https://mlsanity.com/paper/2311.17431/) (2023)
- [ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via α-β-Divergence](https://mlsanity.com/paper/2505.04560/) (2025)
- [Large Multimodal Model Compression via Efficient Pruning and Distillation at AntGroup](https://mlsanity.com/paper/2312.05795/) (2023)
- [Towards Incremental Learning in Large Language Models: A Critical Review](https://mlsanity.com/paper/2404.18311/) (2024)
- [Feature Alignment and Representation Transfer in Knowledge Distillation for Large Language Models](https://mlsanity.com/paper/2504.13825/) (2025)
- [Task-agnostic Distillation of Encoder-Decoder Language Models](https://mlsanity.com/paper/2305.12330/) (2023)
- [Deploying Foundation Model Powered Agent Services: A Survey](https://mlsanity.com/paper/2412.13437/) (2024)
- [Learning Task-Agnostic Representations through Multi-Teacher Distillation](https://mlsanity.com/paper/2510.18680/) (2025)
- [VTrans: Accelerating Transformer Compression with Variational Information Bottleneck based Pruning](https://mlsanity.com/paper/2406.05276/) (2024)
- [Theoretical Guarantees for Low-Rank Compression of Deep Neural Networks](https://mlsanity.com/paper/2502.02766/) (2025)
- [DONUT-hole: DONUT Sparsification by Harnessing Knowledge and Optimizing Learning Efficiency](https://mlsanity.com/paper/2311.05778/) (2023)
- [Comb, Prune, Distill: Towards Unified Pruning for Vision Model Compression](https://mlsanity.com/paper/2408.03046/) (2024)
- [IDEA Prune: An Integrated Enlarge-and-Prune Pipeline in Generative Language Model Pretraining](https://mlsanity.com/paper/2503.05920/) (2025)
- [Dynamic Self-Distillation via Previous Mini-batches for Fine-tuning Small Language Models](https://mlsanity.com/paper/2411.16991/) (2024)
- [TT-MPD: Test Time Model Pruning and Distillation](https://mlsanity.com/paper/2412.07114/) (2024)
- [A Study on Hidden Layer Distillation for Large Language Model Pre-Training](https://mlsanity.com/paper/2605.11513/) (2026)
- [A Unified Approach to Interpreting Knowledge Distillation for Large Language Models via Interactions](https://mlsanity.com/paper/2607.08776/) (2026)
- [KDFP: A first-principles approach to knowledge distillation in large language models](https://mlsanity.com/paper/2610.10854/) (2026)

## Abstract (arXiv)

Knowledge distillation has been shown to be a powerful model compression approach to facilitate the deployment of pre-trained language models in practice. This paper focuses on task-agnostic distillation. It produces a compact pre-trained model that can be easily fine-tuned on various tasks with small computational costs and memory footprints. Despite the practical benefits, task-agnostic distillation is challenging. Since the teacher model has a significantly larger capacity and stronger representation power than the student model, it is very difficult for the student to produce predictions that match the teacher's over a massive amount of open-domain training data. Such a large prediction discrepancy often diminishes the benefits of knowledge distillation. To address this challenge, we propose Homotopic Distillation (HomoDistil), a novel task-agnostic distillation approach equipped with iterative pruning. Specifically, we initialize the student model from the teacher model, and iteratively prune the student's neurons until the target width is reached. Such an approach maintains a small discrepancy between the teacher's and student's predictions throughout the distillation process, which ensures the effectiveness of knowledge transfer. Extensive experiments demonstrate that HomoDistil achieves significant improvements on existing baselines.