paper-with-me

홈 › Papers

Understanding The Effectiveness of Lossy Compression in Machine Learning Training Sets

2024-03-23 · Robert Underwood, Jon C. Calhoun, Sheng Di, Franck Cappello

Learning and Artificial Intelligence (ML/AI) techniques have become increasingly prevalent in high performance computing (HPC). However, these methods depend on vast volumes of floating point data for training and validation which need methods to share the data on a wide area network (WAN) or to transfer it from edge devices to data centers. Data compression can be a solution to these problems, but an in-depth understanding of how lossy compression affects model quality is needed. Prior work largely considers a single application or compression method. We designed a systematic methodology for evaluating data reduction techniques for ML/AI, and we use it to perform a very comprehensive evaluation with 17 data reduction methods on 7 ML/AI applications to show modern lossy compression methods can achieve a 50-100x compression ratio improvement for a 1% or less loss in quality. We identify critical insights that guide the future use and design of lossy compressors for ML/AI.

📄 PDF Abstract BibTeX arXiv:2403.15953

Code (0)

등록된 구현이 없습니다.

Tasks

Data Compression

Similar Papers 제목 키워드 기반

Machine Perceptual Quality: Evaluating the Impact of Severe Lossy Compression on Audio and Image Models

2024-01-15 · Dan Jacobellis, Daniel Cummings, Neeraja J. Yadwadkar

In the field of neural data compression, the prevailing focus has been on optimizing algorithms for either classical distortion metrics, such as PSNR or SSIM, or human perceptual quality. With increasing amounts of data …

Data Compressionimage-classificationImage ClassificationImage Segmentation+5

Everyone Can Attack: Repurpose Lossy Compression as a Natural Backdoor Attack

2023-08-31 · Sze Jue Yang, Quang Nguyen, Chee Seng Chan, Khoa D. Doan

The vulnerabilities to backdoor attacks have recently threatened the trustworthiness of machine learning models in practical applications. Conventional wisdom suggests that not everyone can be an attacker since the proce…

Backdoor AttackImage Compression

Lossy Compression of Adjacency Matrices by Graph Filter Banks

2024-02-05 · Kenta Yanagiya, Junya Hara, Hiroshi Higashi, Yuichi Tanaka 외

This paper proposes a compression framework for adjacency matrices of weighted graphs based on graph filter banks. Adjacency matrices are widely used mathematical representations of graphs and are used in various applica…

Crowd Counting on Heavily Compressed Images with Curriculum Pre-Training

2022-08-15 · Arian Bakhtiarnia, Qi Zhang, Alexandros Iosifidis

JPEG image compression algorithm is a widely used technique for image size reduction in edge and cloud computing settings. However, applying such lossy compression on images processed by deep neural networks can lead to …

Cloud ComputingCrowd CountingImage Compression

Universal End-to-End Neural Network for Lossy Image Compression

2024-09-10 · Bouzid Arezki, Fangchen Feng, Anissa Mokraoui

This paper presents variable bitrate lossy image compression using a VAE-based neural network. An adaptable image quality adjustment strategy is proposed. The key innovation involves adeptly adjusting the input scale exc…

Image CompressionSSIM