SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting

• URL: http://arxiv.org/abs/2503.08668v2
• Date: Sun, 03 Aug 2025 18:28:36 GMT
• Title: SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting
• Authors: Shuaiting Li, Juncan Deng, Chenxuan Wang, Kedong Xu, Rongtao Deng, Hong Gu, Haibin Shen, Kejie Huang,
• Abstract summary: We introduce a novel VQ paradigm, Sign-Splitting VQ (SSVQ), which decouples the sign bit of weights from the codebook.<n>We show that SSVQ achieves a significantly superior compression-accuracy trade-off compared to conventional VQ.
• Score: 7.663974702092357
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vector Quantization (VQ) has emerged as a prominent weight compression technique, showcasing substantially lower quantization errors than uniform quantization across diverse models, particularly in extreme compression scenarios. However, its efficacy during fine-tuning is limited by the constraint of the compression format, where weight vectors assigned to the same codeword are restricted to updates in the same direction. Consequently, many quantized weights are compelled to move in directions contrary to their local gradient information. To mitigate this issue, we introduce a novel VQ paradigm, Sign-Splitting VQ (SSVQ), which decouples the sign bit of weights from the codebook. Our approach involves extracting the sign bits of uncompressed weights and performing clustering and compression on all-positive weights. We then introduce latent variables for the sign bit and jointly optimize both the signs and the codebook. Additionally, we implement a progressive freezing strategy for the learnable sign to ensure training stability. Extensive experiments on various modern models and tasks demonstrate that SSVQ achieves a significantly superior compression-accuracy trade-off compared to conventional VQ. Furthermore, we validate our algorithm on a hardware accelerator, showing that SSVQ achieves a 3$\times$ speedup over the 8-bit compressed model by reducing memory access. Our code is available at https://github.com/list0830/SSVQ.

Related papers

• Multi-Scale Invertible Neural Network for Wide-Range Variable-Rate Learned Image Compression [90.59962443790593]
  In this paper, we present a variable-rate image compression model based on invertible transform to overcome limitations. Specifically, we design a lightweight multi-scale invertible neural network, which maps the input image into multi-scale latent representations. Experimental results demonstrate that the proposed method achieves state-of-the-art performance compared to existing variable-rate methods.
  arXiv  Detail & Related papers  (2025-03-27T09:08:39Z)
• CondiQuant: Condition Number Based Low-Bit Quantization for Image Super-Resolution [59.91470739501034]
  We propose CondiQuant, a condition number based low-bit post-training quantization for image super-resolution. We show that CondiQuant outperforms existing state-of-the-art post-training quantization methods in accuracy without computation overhead.
  arXiv  Detail & Related papers  (2025-02-21T14:04:30Z)
• Scalable Image Tokenization with Index Backpropagation Quantization [74.15447383432262]
  Index Backpropagation Quantization (IBQ) is a new VQ method for the joint optimization of all codebook embeddings and the visual encoder.<n>IBQ enables scalable training of visual tokenizers and, for the first time, achieves a large-scale codebook with high dimension ($256$) and high utilization.
  arXiv  Detail & Related papers  (2024-12-03T18:59:10Z)
• QTIP: Quantization with Trellises and Incoherence Processing [29.917017118524246]
  Post-training quantization (PTQ) reduces the memory footprint of LLMs. Recent state-of-the-art PTQ approaches use vector quantization (VQ) to quantize multiple weights at once. We introduce QTIP, which instead uses trellis coded quantization (TCQ) to achieve ultra-high-dimensional quantization.
  arXiv  Detail & Related papers  (2024-06-17T06:03:13Z)
• HyperVQ: MLR-based Vector Quantization in Hyperbolic Space [56.4245885674567]
  A common solution is to employ Vector Quantization (VQ) within VQ Variational Autoencoders (VQVAEs) We introduce HyperVQ, a novel approach that formulates VQ as a hyperbolic Multinomial Logistic Regression (MLR) problem. Our experiments demonstrate that HyperVQ matches traditional VQ in generative and reconstruction tasks, while surpassing it in discriminative performance.
  arXiv  Detail & Related papers  (2024-03-18T03:17:08Z)
• GPTVQ: The Blessing of Dimensionality for LLM Quantization [16.585681547799762]
  We show that the size versus accuracy trade-off of neural network quantization can be significantly improved by increasing the quantization dimensionality. We propose the GPTVQ method, a new fast method for post-training vector quantization (VQ) that scales well to Large Language Models (LLMs) Our method interleaves quantization of one or more columns with updates to the remaining unquantized weights, using information from the Hessian of the per-layer output reconstruction MSE.
  arXiv  Detail & Related papers  (2024-02-23T13:39:16Z)
• Activations and Gradients Compression for Model-Parallel Training [85.99744701008802]
  We study how simultaneous compression of activations and gradients in model-parallel distributed training setup affects convergence. We find that gradients require milder compression rates than activations. Experiments also show that models trained with TopK perform well only when compression is also applied during inference.
  arXiv  Detail & Related papers  (2024-01-15T15:54:54Z)
• Extreme Compression of Large Language Models via Additive Quantization [59.3122859349777]
  Our algorithm, called AQLM, generalizes the classic Additive Quantization (AQ) approach for information retrieval. We provide fast GPU and CPU implementations of AQLM for token generation, which enable us to match or outperform optimized FP16 implementations for speed.
  arXiv  Detail & Related papers  (2024-01-11T18:54:44Z)
• Soft Convex Quantization: Revisiting Vector Quantization with Convex Optimization [40.1651740183975]
  We propose Soft Convex Quantization (SCQ) as a direct substitute for Vector Quantization (VQ) SCQ works like a differentiable convex optimization (DCO) layer. We demonstrate its efficacy on the CIFAR-10, GTSRB and LSUN datasets.
  arXiv  Detail & Related papers  (2023-10-04T17:45:14Z)
• Finite Scalar Quantization: VQ-VAE Made Simple [26.351016719675766]
  We propose to replace vector quantization (VQ) in the latent representation of VQ-VAEs with a simple scheme termed finite scalar quantization (FSQ) By appropriately choosing the number of dimensions and values each dimension can take, we obtain the same codebook size as in VQ. We employ FSQ with MaskGIT for image generation, and with UViM for depth estimation, colorization, and panoptic segmentation.
  arXiv  Detail & Related papers  (2023-09-27T09:13:40Z)
• Extreme Image Compression using Fine-tuned VQGANs [43.43014096929809]
  We introduce vector quantization (VQ)-based generative models into the image compression domain. The codebook learned by the VQGAN model yields a strong expressive capacity. The proposed framework outperforms state-of-the-art codecs in terms of perceptual quality-oriented metrics.
  arXiv  Detail & Related papers  (2023-07-17T06:14:19Z)
• LVQAC: Lattice Vector Quantization Coupled with Spatially Adaptive Companding for Efficient Learned Image Compression [24.812267280543693]
  We present a novel Lattice Vector Quantization scheme coupled with a spatially Adaptive Companding (LVQAC) mapping. For any end-to-end CNN image compression models, replacing uniform quantizer by LVQAC achieves better rate-distortion performance without significantly increasing the model complexity.
  arXiv  Detail & Related papers  (2023-03-25T23:34:15Z)
• Image Compression with Product Quantized Masked Image Modeling [44.15706119017024]
  Recent neural compression methods have been based on the popular hyperprior framework. It relies on Scalar Quantization and offers a very strong compression performance. This contrasts from recent advances in image generation and representation learning, where Vector Quantization is more commonly employed.
  arXiv  Detail & Related papers  (2022-12-14T17:50:39Z)
• Kernel Quantization for Efficient Network Compression [59.55192551370948]
  Kernel Quantization (KQ) aims to efficiently convert any pre-trained full-precision convolutional neural network (CNN) model into a low-precision version without significant performance loss. Inspired by the evolution from weight pruning to filter pruning, we propose to quantize in both kernel and weight level. Experiments on the ImageNet classification task prove that KQ needs 1.05 and 1.62 bits on average in VGG and ResNet18, respectively, to represent each parameter in the convolution layer.
  arXiv  Detail & Related papers  (2020-03-11T08:00:04Z)

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.