Big2Small: A Unifying Neural Network Framework for Model Compression

• URL: http://arxiv.org/abs/2603.29768v1
• Date: Tue, 31 Mar 2026 14:09:19 GMT
• Title: Big2Small: A Unifying Neural Network Framework for Model Compression
• Abstract summary: We construct a unifying mathematical framework for model compression grounded in measure theory.<n>We show that each model compression technique is mathematically equivalent to a neural network subject to a regularization.<n>We propose an experimentally-verified data-free model compression framework, termed textitBig2Small, which translates Implicit Neural Representations (INRs) from data domain to domain of network parameters.
• Score: 14.509737343784913
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the development of foundational models, model compression has become a critical requirement. Various model compression approaches have been proposed such as low-rank decomposition, pruning, quantization, ergodic dynamic systems, and knowledge distillation, which are based on different heuristics. To elevate the field from fragmentation to a principled discipline, we construct a unifying mathematical framework for model compression grounded in measure theory. We further demonstrate that each model compression technique is mathematically equivalent to a neural network subject to a regularization. Building upon this mathematical and structural equivalence, we propose an experimentally-verified data-free model compression framework, termed \textit{Big2Small}, which translates Implicit Neural Representations (INRs) from data domain to the domain of network parameters. \textit{Big2Small} trains compact INRs to encode the weights of larger models and reconstruct the weights during inference. To enhance reconstruction fidelity, we introduce Outlier-Aware Preprocessing to handle extreme weight values and a Frequency-Aware Loss function to preserve high-frequency details. Experiments on image classification and segmentation demonstrate that \textit{Big2Small} achieves competitive accuracy and compression ratios compared to state-of-the-art baselines.

Related papers

• Hybrid Compression: Integrating Pruning and Quantization for Optimized Neural Networks [10.505297793600137]
  We propose a novel method for model compression through two phases.<n>First, we utilize model compression techniques, such as pruning and quantization, to significantly reduce the model size.<n>Then, we use Mixture of Experts to route the previously compressed models to enhance performance while maintaining a balance in inference efficiency.
  arXiv  Detail & Related papers  (2026-06-22T07:11:52Z)
• Arbitrary Ratio Feature Compression via Next Token Prediction [52.10426317889982]
  Arbitrary Ratio Feature Compression (ARFC) framework supports any compression ratio with a single model.<n>ARC is an auto-regressive model that performs compression via next-gressive prediction.<n>MoS module refines the compressed tokens by utilizing multiple compression results.<n>ERGC is integrated into the training process to preserve semantic and structural relationships during compression.
  arXiv  Detail & Related papers  (2026-02-12T02:38:57Z)
• Knowledge-Informed Neural Network for Complex-Valued SAR Image Recognition [51.03674130115878]
  We introduce the Knowledge-Informed Neural Network (KINN), a lightweight framework built upon a novel "compression-aggregation-compression" architecture.<n>KINN establishes a state-of-the-art in parameter-efficient recognition, offering exceptional generalization in data-scarce and out-of-distribution scenarios.
  arXiv  Detail & Related papers  (2025-10-23T07:12:26Z)
• On Information Geometry and Iterative Optimization in Model Compression: Operator Factorization [5.952537659103525]
  We argue that many successful model compression approaches can be understood as implicitly approximating information divergences for this projection.<n>We prove convergence of iterative singular value thresholding for training neural networks subject to a soft rank constraint.
  arXiv  Detail & Related papers  (2025-07-12T23:39:14Z)
• Theoretical Guarantees for Low-Rank Compression of Deep Neural Networks [5.582683296425384]
  Deep neural networks have achieved state-of-the-art performance across numerous applications.<n>Low-rank approximation techniques offer a promising solution by reducing the size and complexity of these networks.<n>We develop an analytical framework for data-driven post-training low-rank compression.
  arXiv  Detail & Related papers  (2025-02-04T23:10:13Z)
• Convolutional Neural Network Compression Based on Low-Rank Decomposition [3.3295360710329738]
  This paper proposes a model compression method that integrates Variational Bayesian Matrix Factorization. VBMF is employed to estimate the rank of the weight tensor at each layer. Experimental results show that for both high and low compression ratios, our compression model exhibits advanced performance.
  arXiv  Detail & Related papers  (2024-08-29T06:40:34Z)
• 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)
• Retraining-free Model Quantization via One-Shot Weight-Coupling Learning [41.299675080384]
  Mixed-precision quantization (MPQ) is advocated to compress the model effectively by allocating heterogeneous bit-width for layers. MPQ is typically organized into a searching-retraining two-stage process. In this paper, we devise a one-shot training-searching paradigm for mixed-precision model compression.
  arXiv  Detail & Related papers  (2024-01-03T05:26:57Z)
• Rethinking Compression: Reduced Order Modelling of Latent Features in Large Language Models [9.91972450276408]
  This paper introduces an innovative approach for the parametric and practical compression of Large Language Models (LLMs) based on reduced order modelling. Our method represents a significant advancement in model compression by leveraging matrix decomposition, demonstrating superior efficacy compared to the prevailing state-of-the-art structured pruning method.
  arXiv  Detail & Related papers  (2023-12-12T07:56:57Z)
• What do Compressed Large Language Models Forget? Robustness Challenges in Model Compression [68.82486784654817]
  We study two popular model compression techniques including knowledge distillation and pruning. We show that compressed models are significantly less robust than their PLM counterparts on adversarial test sets. We develop a regularization strategy for model compression based on sample uncertainty.
  arXiv  Detail & Related papers  (2021-10-16T00:20:04Z)
• Compact representations of convolutional neural networks via weight pruning and quantization [63.417651529192014]
  We propose a novel storage format for convolutional neural networks (CNNs) based on source coding and leveraging both weight pruning and quantization. We achieve a reduction of space occupancy up to 0.6% on fully connected layers and 5.44% on the whole network, while performing at least as competitive as the baseline.
  arXiv  Detail & Related papers  (2021-08-28T20:39:54Z)
• Structured Sparsification with Joint Optimization of Group Convolution and Channel Shuffle [117.95823660228537]
  We propose a novel structured sparsification method for efficient network compression. The proposed method automatically induces structured sparsity on the convolutional weights. We also address the problem of inter-group communication with a learnable channel shuffle mechanism.
  arXiv  Detail & Related papers  (2020-02-19T12:03:10Z)

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.