Foundation Model for Lossy Compression of Spatiotemporal Scientific Data

• URL: http://arxiv.org/abs/2412.17184v1
• Date: Sun, 22 Dec 2024 22:57:08 GMT
• Title: Foundation Model for Lossy Compression of Spatiotemporal Scientific Data
• Authors: Xiao Li, Jaemoon Lee, Anand Rangarajan, Sanjay Ranka,
• Abstract summary: We present a foundation model (FM) for lossy scientific data compression. We combine a variational autoencoder (E) with a hyper-prior structure and a super-resolution (SR) module.
• Score: 11.494915987840876
• License:
• Abstract: We present a foundation model (FM) for lossy scientific data compression, combining a variational autoencoder (VAE) with a hyper-prior structure and a super-resolution (SR) module. The VAE framework uses hyper-priors to model latent space dependencies, enhancing compression efficiency. The SR module refines low-resolution representations into high-resolution outputs, improving reconstruction quality. By alternating between 2D and 3D convolutions, the model efficiently captures spatiotemporal correlations in scientific data while maintaining low computational cost. Experimental results demonstrate that the FM generalizes well to unseen domains and varying data shapes, achieving up to 4 times higher compression ratios than state-of-the-art methods after domain-specific fine-tuning. The SR module improves compression ratio by 30 percent compared to simple upsampling techniques. This approach significantly reduces storage and transmission costs for large-scale scientific simulations while preserving data integrity and fidelity.

Related papers

• Guaranteed Conditional Diffusion: 3D Block-based Models for Scientific Data Compression [10.848192105624848]
  This paper proposes a new compression paradigm -- Guaranteed Diffusion with Conditional Correction (GCDTC) It consists of a conditional diffusion model, tensor correction, and error guarantee. Our framework outperforms standard convolutional autoencoders and yields competitive compression quality with an existing scientific data compression algorithm.
  arXiv  Detail & Related papers  (2025-02-18T15:33:09Z)
• Factorized Implicit Global Convolution for Automotive Computational Fluid Dynamics Prediction [52.32698071488864]
  We propose Factorized Implicit Global Convolution (FIGConv), a novel architecture that efficiently solves CFD problems for very large 3D meshes. FIGConv achieves quadratic complexity $O(N2)$, a significant improvement over existing 3D neural CFD models. We validate our approach on the industry-standard Ahmed body dataset and the large-scale DrivAerNet dataset.
  arXiv  Detail & Related papers  (2025-02-06T18:57:57Z)
• NeurLZ: On Enhancing Lossy Compression Performance based on Error-Controlled Neural Learning for Scientific Data [35.36879818366783]
  Large-scale scientific simulations generate massive datasets that pose challenges for storage and I/O. We propose NeurLZ, a novel cross-field learning-based and error-controlled compression framework for scientific data.
  arXiv  Detail & Related papers  (2024-09-09T16:48:09Z)
• MoDeGPT: Modular Decomposition for Large Language Model Compression [59.361006801465344]
  This paper introduces textbfModular bfDecomposition (MoDeGPT), a novel structured compression framework. MoDeGPT partitions the Transformer block into modules comprised of matrix pairs and reduces the hidden dimensions. Our experiments show MoDeGPT, without backward propagation, matches or surpasses previous structured compression methods.
  arXiv  Detail & Related papers  (2024-08-19T01:30:14Z)
• Generalized Nested Latent Variable Models for Lossy Coding applied to Wind Turbine Scenarios [14.48369551534582]
  A learning-based approach seeks to minimize the compromise between compression rate and reconstructed image quality. A successful technique consists in introducing a deep hyperprior that operates within a 2-level nested latent variable model. This paper extends this concept by designing a generalized L-level nested generative model with a Markov chain structure.
  arXiv  Detail & Related papers  (2024-06-10T11:00:26Z)
• Fed-CVLC: Compressing Federated Learning Communications with Variable-Length Codes [54.18186259484828]
  In Federated Learning (FL) paradigm, a parameter server (PS) concurrently communicates with distributed participating clients for model collection, update aggregation, and model distribution over multiple rounds. We show strong evidences that variable-length is beneficial for compression in FL. We present Fed-CVLC (Federated Learning Compression with Variable-Length Codes), which fine-tunes the code length in response to the dynamics of model updates.
  arXiv  Detail & Related papers  (2024-02-06T07:25:21Z)
• Hierarchical Integration Diffusion Model for Realistic Image Deblurring [71.76410266003917]
  Diffusion models (DMs) have been introduced in image deblurring and exhibited promising performance. We propose the Hierarchical Integration Diffusion Model (HI-Diff), for realistic image deblurring. Experiments on synthetic and real-world blur datasets demonstrate that our HI-Diff outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-05-22T12:18:20Z)
• Transform Once: Efficient Operator Learning in Frequency Domain [69.74509540521397]
  We study deep neural networks designed to harness the structure in frequency domain for efficient learning of long-range correlations in space or time. This work introduces a blueprint for frequency domain learning through a single transform: transform once (T1)
  arXiv  Detail & Related papers  (2022-11-26T01:56:05Z)
• Efficient Data Compression for 3D Sparse TPC via Bicephalous Convolutional Autoencoder [8.759778406741276]
  This work introduces a dual-head autoencoder to resolve sparsity and regression simultaneously, called textitBicephalous Convolutional AutoEncoder (BCAE) It shows advantages both in compression fidelity and ratio compared to traditional data compression methods, such as MGARD, SZ, and ZFP.
  arXiv  Detail & Related papers  (2021-11-09T21:26:37Z)
• Fourier Space Losses for Efficient Perceptual Image Super-Resolution [131.50099891772598]
  We show that it is possible to improve the performance of a recently introduced efficient generator architecture solely with the application of our proposed loss functions. We show that our losses' direct emphasis on the frequencies in Fourier-space significantly boosts the perceptual image quality. The trained generator achieves comparable results with and is 2.4x and 48x faster than state-of-the-art perceptual SR methods RankSRGAN and SRFlow respectively.
  arXiv  Detail & Related papers  (2021-06-01T20:34:52Z)

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.