This paper proposes a novel compression method that uses Singular Value Decomposition (SVD) informed by data examples that achieves substantial reductions in model size and computation with minimal impact on accuracy and demonstrates its applicability in compressing deep neural networks to a fraction of their original size.
Abstract
Deep neural network compression focuses on reducing the number of parameters and computational complexity of neural networks, enabling their use in resource-constrained environments where smaller networks, faster response times, and lower energy consumption are critical. In this paper, we propose a novel compression method that uses Singular Value Decomposition (SVD) informed by data examples. Unlike existing SVD-based approaches that operate solely on network weights, our method leverages input data to more effectively preserve essential information during compression. This data-driven approach significantly enhances performance compared to state-of-the-art techniques. Through experiments on standard benchmark datasets, we show that our method achieves substantial reductions in model size and computation with minimal impact on accuracy. Furthermore, we demonstrate its applicability in compressing deep neural networks to a fraction of their original size, achieving competitive accuracy of networks with a compression ratio of less than 3× with no fine-tuning, and at most 25 epochs of fine-tuning for higher compression ratios.
Experimental results demonstrate that effective compression significantly reduces model size and computational cost with minimal performance loss, highlighting the importance of compression-aware design and concluding as a valuable reference for building efficient and scalable AI systems.
Daniel Rodríguez· International Journal of App...· 0 citations
The proposed hybrid pipeline includes structured pruning, INT8 quantization and task-specific knowledge distillation, which is benchmarked against standalone methods and reinforces the idea of upper bound projection based approach for accuracy-oriented, multi-level compression.
Krishna Kumar Tiwari, Komal Tahiliani, Uma Shankar Birthare et al.· International journal of com...· 0 citations
Findings confirm that combining complementary compression strategies yields substantially better performance-efficiency trade-offs than any single technique applied in isolation.
Upma Sharma Archana· International Journal of Res...· 0 citations
It has long been known that well-trained neural networks can be compressed very strongly without affecting their performance, an important phenomenon that remains poorly understood. We prove a uniform compressibility theorem for deep multilayer perceptrons with analytic activations. For a deep, wide fixed teacher network, there exists a narrow (same depth) network that approximately represents the same function as the original. The reachable compressed width is strikingly independent of the original width, but is $O((\log(1/\varepsilon))^{d_{in}})$, where $\varepsilon$ is the error budget and $d_{in}$ is the effective input dimension. Our construction involves a novel derivative-matching technique which is aware of the low-dimensional input, and a layer-wise reweighting that preserves the input-output mapping.
Large-scale scientific simulations generate volumetric data at rates that far outpace advances in storage and network bandwidth, making effective lossy compression increasingly critical. However, conventional compressors often struggle to preserve fine structural details at high compression ratios (CRs), and implicit neural representations (INRs) require costly per-volume optimization and produce models with fixed CRs. To respond, we present EVOLVE, an autoencoder (AE)-based volume-compression framework that targets high CRs for offline compression, with three key contributions. First, we construct a large-scale cross-domain database of 6,376 volumes from 21 scientific simulations, curated via perceptual hashing to ensure diversity, enabling the optimized model to extract features that generalize across volumes within the covered scientific simulation domains. Second, we reexamine the design space of AE-based compressors and incorporate several macro- and micro-designs into a vanilla AE to develop EVOLVE, which substantially improves the expressive power and compression capability. Third, we develop a learnable gain mechanism with a three-stage training strategy to enable variable-rate encoding, allowing a single model to support continuous CR adjustment at inference time. Experiments on multiple unseen scientific simulation datasets demonstrate that EVOLVE achieves substantially higher CRs than conventional compressors at comparable reconstruction quality, while delivering compression speeds that are orders of magnitude faster than INR-based methods, highlighting its promise as a strong alternative for compressing scientific data. The code, model weights, and results are available on our project page at https://evolve-vis.github.io.
Traditional model reduction techniques for neural network compression usually leverage existing matrix/tensor decomposition methods to explore the redundancy among model parameters, which may overlook the local structures of the models. In this work, we propose a novel low-rank approximation algorithm, called Dimension-Augmented Tensor-Train (DATT) decomposition, which integrates dimension slicing with the Tensor-Train decomposition. DATT allows different partitions to be represented using distinct, non-shared spanning sets. This enables the decomposition to adapt more flexibly to localized structure, potentially achieving better compression. With the localized low-rank structures, DATT provides a more compact representation of neural network weights. We evaluated the performance of DATT with the other state-of-the-art low-rank approximation-based model compression algorithms, and demonstrated that DATT outperforms them in terms of parameter reduction and model accuracy. In particular, for compressing ResNet-20 on CIFAR-10, DATT achieves a 77.00% reduction in parameters with only a 0.37% drop in top-1 accuracy.
Yu-Chuan Tai, Cheng-Yu Sie, Che-Rung Lee· Annual International Compute...· 0 citations