# PC-LoRA: Low-Rank Adaptation for Progressive Model Compression with Knowledge Distillation

arXiv: https://arxiv.org/abs/2406.09117 · HTML: https://mlsanity.com/paper/2406.09117/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Knowledge distillation for LLMs, one of 12 directions in Knowledge distillation.
- Builds on 16 of its 23 references that are in the map.
- First posted on arXiv 13 Jun 2024.

## Placed in

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

## Builds on (most cited first, 16 of 16)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Rethinking the Value of Network Pruning](https://mlsanity.com/paper/1810.05270/) (2018)
- [Knowledge Transfer via Distillation of Activation Boundaries Formed by Hidden Neurons](https://mlsanity.com/paper/1811.03233/) (2018)
- [Learning Deep Representations with Probabilistic Knowledge Transfer](https://mlsanity.com/paper/1803.10837/) (2018)
- [Language model compression with weighted low-rank factorization](https://mlsanity.com/paper/2207.00112/) (2022)

## Built on by (most cited first, 9 of 9)

- [LatentLLM: Attention-Aware Joint Tensor Compression](https://mlsanity.com/paper/2505.18413/) (2025)
- [μ-MoE: Test-Time Pruning as Micro-Grained Mixture-of-Experts](https://mlsanity.com/paper/2505.18451/) (2025)
- [Demystifying Low-Rank Knowledge Distillation in Large Language Models: Convergence, Generalization, and Information-Theoretic Guarantees](https://mlsanity.com/paper/2603.22355/) (2026)
- [TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference On The Fly](https://mlsanity.com/paper/2603.19296/) (2026)
- [TuneComp: Joint Fine-tuning and Compression for Large Foundation Models](https://mlsanity.com/paper/2505.21835/) (2025)
- [Compress Then Adapt? No, Do It Together via Task-aware Union of Subspaces](https://mlsanity.com/paper/2605.02829/) (2026)
- [Budgeted LoRA: Distillation as Structured Compute Allocation for Efficient Inference](https://mlsanity.com/paper/2605.04341/) (2026)
- [EinSort: Sorting is All We Need for Tensorizing LLM](https://mlsanity.com/paper/2606.08565/) (2026)
- [SAD-LoRA: Spectral Alignment for Low-Rank Knowledge Distillation](https://mlsanity.com/paper/2607.04306/) (2026)

## Abstract (arXiv)

Low-rank adaption (LoRA) is a prominent method that adds a small number of learnable parameters to the frozen pre-trained weights for parameter-efficient fine-tuning. Prompted by the question, ``Can we make its representation enough with LoRA weights solely at the final phase of finetuning without the pre-trained weights?'' In this work, we introduce Progressive Compression LoRA~(PC-LoRA), which utilizes low-rank adaptation (LoRA) to simultaneously perform model compression and fine-tuning. The PC-LoRA method gradually removes the pre-trained weights during the training process, eventually leaving only the low-rank adapters in the end. Thus, these low-rank adapters replace the whole pre-trained weights, achieving the goals of compression and fine-tuning at the same time. Empirical analysis across various models demonstrates that PC-LoRA achieves parameter and FLOPs compression rates of 94.36%/89.1% for vision models, e.g., ViT-B, and 93.42%/84.2% parameters and FLOPs compressions for language models, e.g., BERT.