DeepCQ: General-Purpose Deep-Surrogate Framework for Lossy Compression Quality Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mumenin, Khondoker Mirazul, Underwood, Robert, Dai, Dong, Wang, Jinzhen, Di, Sheng, Lukić, Zarija, Cappello, Franck
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912788996161536
author Mumenin, Khondoker Mirazul
Underwood, Robert
Dai, Dong
Wang, Jinzhen
Di, Sheng
Lukić, Zarija
Cappello, Franck
author_facet Mumenin, Khondoker Mirazul
Underwood, Robert
Dai, Dong
Wang, Jinzhen
Di, Sheng
Lukić, Zarija
Cappello, Franck
contents Error-bounded lossy compression techniques have become vital for scientific data management and analytics, given the ever-increasing volume of data generated by modern scientific simulations and instruments. Nevertheless, assessing data quality post-compression remains computationally expensive due to the intensive nature of metric calculations. In this work, we present a general-purpose deep-surrogate framework for lossy compression quality prediction (DeepCQ), with the following key contributions: 1) We develop a surrogate model for compression quality prediction that is generalizable to different error-bounded lossy compressors, quality metrics, and input datasets; 2) We adopt a novel two-stage design that decouples the computationally expensive feature-extraction stage from the light-weight metrics prediction, enabling efficient training and modular inference; 3) We optimize the model performance on time-evolving data using a mixture-of-experts design. Such a design enhances the robustness when predicting across simulation timesteps, especially when the training and test data exhibit significant variation. We validate the effectiveness of DeepCQ on four real-world scientific applications. Our results highlight the framework's exceptional predictive accuracy, with prediction errors generally under 10\% across most settings, significantly outperforming existing methods. Our framework empowers scientific users to make informed decisions about data compression based on their preferred data quality, thereby significantly reducing I/O and computational overhead in scientific data analysis.
format Preprint
id arxiv_https___arxiv_org_abs_2512_21433
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeepCQ: General-Purpose Deep-Surrogate Framework for Lossy Compression Quality Prediction
Mumenin, Khondoker Mirazul
Underwood, Robert
Dai, Dong
Wang, Jinzhen
Di, Sheng
Lukić, Zarija
Cappello, Franck
Machine Learning
Distributed, Parallel, and Cluster Computing
Performance
Error-bounded lossy compression techniques have become vital for scientific data management and analytics, given the ever-increasing volume of data generated by modern scientific simulations and instruments. Nevertheless, assessing data quality post-compression remains computationally expensive due to the intensive nature of metric calculations. In this work, we present a general-purpose deep-surrogate framework for lossy compression quality prediction (DeepCQ), with the following key contributions: 1) We develop a surrogate model for compression quality prediction that is generalizable to different error-bounded lossy compressors, quality metrics, and input datasets; 2) We adopt a novel two-stage design that decouples the computationally expensive feature-extraction stage from the light-weight metrics prediction, enabling efficient training and modular inference; 3) We optimize the model performance on time-evolving data using a mixture-of-experts design. Such a design enhances the robustness when predicting across simulation timesteps, especially when the training and test data exhibit significant variation. We validate the effectiveness of DeepCQ on four real-world scientific applications. Our results highlight the framework's exceptional predictive accuracy, with prediction errors generally under 10\% across most settings, significantly outperforming existing methods. Our framework empowers scientific users to make informed decisions about data compression based on their preferred data quality, thereby significantly reducing I/O and computational overhead in scientific data analysis.
title DeepCQ: General-Purpose Deep-Surrogate Framework for Lossy Compression Quality Prediction
topic Machine Learning
Distributed, Parallel, and Cluster Computing
Performance
url https://arxiv.org/abs/2512.21433