TuneComp: Joint Fine-tuning and Compression for Large Foundation Models

2025-05-27

AI Summary

The conventional “fine-tune-then-compress” paradigm for lightweighting large language models (LLMs) during post-training incurs significant performance degradation and introduces redundant intermediate models. Method: This paper proposes the first end-to-end framework that jointly optimizes fine-tuning and structured compression—integrating progressive knowledge distillation, dynamic structured pruning, and low-rank parameter constraints directly into the downstream fine-tuning process to cooperatively shrink the parameter space. Contribution/Results: By eliminating the need to store and compute full-sized intermediate models, our approach reduces memory and computational overhead. On multiple benchmark tasks, it achieves an average accuracy gain of 2.1% at equivalent parameter counts and compresses model size by up to 4.3×, substantially mitigating performance decay inherent in conventional lightweighting pipelines.

Technology Category

Machine Learning: Learning on the Edge & Model CompressionNatural Language Processing: (Large) Language ModelsComputer Vision: Large Vision Models

Application Category

User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendationSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMsEconomics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

To reduce model size during post-training, compression methods, including knowledge distillation, low-rank approximation, and pruning, are often applied after fine-tuning the model. However, sequential fine-tuning and compression sacrifices performance, while creating a larger than necessary model as an intermediate step. In this work, we aim to reduce this gap, by directly constructing a smaller model while guided by the downstream task. We propose to jointly fine-tune and compress the model by gradually distilling it to a pruned low-rank structure. Experiments demonstrate that joint fine-tuning and compression significantly outperforms other sequential compression methods.

Problem

• Jointly fine-tuning and compressing large foundation models
• Reducing performance gap from sequential fine-tuning and compression
• Constructing smaller models guided by downstream tasks

Innovation

• Joint fine-tuning and compression approach
• Gradual distillation to pruned low-rank structure
• Direct construction guided by downstream task