Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression

• URL: http://arxiv.org/abs/2505.13563v2
• Date: Thu, 19 Jun 2025 15:45:16 GMT
• Title: Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression
• Authors: Xiaohui Wang, Peng Ye, Chenyu Huang, Shenghe Zheng, Bo Zhang, Lei Bai, Wanli Ouyang, Tao Chen,
• Abstract summary: UltraDelta is a data-free delta compression pipeline that achieves both ultra-high compression and strong performance.<n>UltraDelta is designed to minimize redundancy, maximize information, and stabilize performance across inter-layer, intra-layer, and global dimensions.
• Score: 53.08742231761896
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the rise of the fine-tuned--pretrained paradigm, storing numerous fine-tuned models for multi-tasking creates significant storage overhead. Delta compression alleviates this by storing only the pretrained model and the highly compressed delta weights (the differences between fine-tuned and pretrained model weights). However, existing methods fail to maintain both high compression and performance, and often rely on data. To address these challenges, we propose UltraDelta, the first data-free delta compression pipeline that achieves both ultra-high compression and strong performance. UltraDelta is designed to minimize redundancy, maximize information, and stabilize performance across inter-layer, intra-layer, and global dimensions, using three key components: (1) Variance-Based Mixed Sparsity Allocation assigns sparsity based on variance, giving lower sparsity to high-variance layers to preserve inter-layer information. (2) Distribution-Aware Compression applies uniform quantization and then groups parameters by value, followed by group-wise pruning, to better preserve intra-layer distribution. (3) Trace-Norm-Guided Rescaling uses the trace norm of delta weights to estimate a global rescaling factor, improving model stability under higher compression. Extensive experiments across (a) large language models (fine-tuned on LLaMA-2 7B and 13B) with up to 133x, (b) general NLP models (RoBERTa-base, T5-base) with up to 800x, (c) vision models (ViT-B/32, ViT-L/14) with up to 400x, and (d) multi-modal models (BEiT-3) with 40x compression ratio, demonstrate that UltraDelta consistently outperforms existing methods, especially under ultra-high compression.

Related papers

• Dynamic Base model Shift for Delta Compression [53.505380509713575]
  Delta compression attempts to lower the costs by reducing the redundancy of delta parameters.<n>Existing methods by default employ the pretrained model as the base model and compress the delta parameters for every task.<n>We propose Dynamic Base Model Shift (DBMS), which dynamically adapts the base model to the target task before performing delta compression.
  arXiv  Detail & Related papers  (2025-05-16T15:11:19Z)
• 4DGC: Rate-Aware 4D Gaussian Compression for Efficient Streamable Free-Viewpoint Video [56.04182926886754]
  3D Gaussian Splatting (3DGS) has substantial potential for enabling photorealistic Free-Viewpoint Video (FVV) experiences.<n>Existing methods typically handle dynamic 3DGS representation and compression separately, motion information and the rate-distortion trade-off during training.<n>We propose 4DGC, a rate-aware 4D Gaussian compression framework that significantly reduces storage size while maintaining superior RD performance for FVV.
  arXiv  Detail & Related papers  (2025-03-24T08:05:27Z)
• Seeing Delta Parameters as JPEG Images: Data-Free Delta Compression with Discrete Cosine Transform [51.29604910007176]
  We introduce Delta-DCT, the first data-free delta compression method inspired by classic JPEG image compression, leveraging the Discrete Cosine Transform (DCT)<n>The proposed Delta-DCT does not require any training or data calibration, while achieving performance comparable to or even surpassing original finetuned models under 1-bit equivalent delta compression ratios on different kinds of models including: (1) recently-released LLMs of different sizes from 7B to 13B, (2) relatively smaller language models including RoBERTa and T5 models, (3) variants of vision transformer models, and (4) multi-modal BEiT-3 models.
  arXiv  Detail & Related papers  (2025-03-09T16:03:48Z)
• GoDe: Gaussians on Demand for Progressive Level of Detail and Scalable Compression [13.616981296093932]
  We propose a novel, model-agnostic technique that organizes Gaussians into several hierarchical layers.<n>This method, combined with recent approach of compression of 3DGS, allows a single model to instantly scale across several compression ratios.<n>We validate our approach on typical datasets and benchmarks, showcasing low distortion and substantial gains in terms of scalability and adaptability.
  arXiv  Detail & Related papers  (2025-01-23T11:05:45Z)
• DeltaDQ: Ultra-High Delta Compression for Fine-Tuned LLMs via Group-wise Dropout and Separate Quantization [17.501956455837707]
  Large language models achieve exceptional performance on various downstream tasks through supervised fine-tuning. Current methods that compress the delta weight struggle to achieve ultra-high compression. We propose a novel distribution-driven delta compression framework DeltaDQ to achieve ultra-high compression for the delta weight.
  arXiv  Detail & Related papers  (2024-10-11T09:44:16Z)
• Compression via Pre-trained Transformers: A Study on Byte-Level Multimodal Data [8.475091996107741]
  This paper investigates whether there is a sweet spot where competitive compression ratios with pre-trained vanilla transformers are possible. We train families of models on 165GB of raw byte sequences of either text, image, or audio data. We find that relatively small models (i.e., millions of parameters) can outperform standard general-purpose compression algorithms.
  arXiv  Detail & Related papers  (2024-10-07T14:32:03Z)
• MoDeGPT: Modular Decomposition for Large Language Model Compression [59.361006801465344]
  This paper introduces textbfModular bfDecomposition (MoDeGPT), a novel structured compression framework.<n>MoDeGPT partitions the Transformer block into modules comprised of matrix pairs and reduces the hidden dimensions.<n>Our experiments show MoDeGPT, without backward propagation, matches or surpasses previous structured compression methods.
  arXiv  Detail & Related papers  (2024-08-19T01:30:14Z)
• Towards Compact CNNs via Collaborative Compression [166.86915086497433]
  We propose a Collaborative Compression scheme, which joints channel pruning and tensor decomposition to compress CNN models. We achieve 52.9% FLOPs reduction by removing 48.4% parameters on ResNet-50 with only a Top-1 accuracy drop of 0.56% on ImageNet 2012.
  arXiv  Detail & Related papers  (2021-05-24T12:07:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.