研究压缩数据对设备端学习的影响，发现应按样本自适应压缩。
Toward Storage-Aware Learning with Compressed Data An Empirical Exploratory Study on JPEG
- 按样本差异性调整压缩率，而非统一处理。
- 不同数据对压缩敏感度不同，影响模型性能。
- 适合资源受限设备的持续学习系统设计。
设备端机器学习常受存储空间限制，尤其在持续数据采集场景下。本文针对存储感知学习展开实证研究，聚焦压缩带来的数据量与质量之间的权衡。结果表明，简单的策略如均匀丢弃数据或统一压缩效果不佳。研究发现数据样本对压缩的敏感度存在差异，支持采用样本级自适应压缩策略。这些发现为构建新型存储感知学习系统奠定基础。主要贡献在于系统性刻画这一未充分探索的挑战，深化了对存储感知学习的理解。
原文摘要 · Abstract (English)
On-device machine learning is often constrained by limited storage, particularly in continuous data collection scenarios. This paper presents an empirical study on storage-aware learning, focusing on the trade-off between data quantity and quality via compression. We demonstrate that naive strategies, such as uniform data dropping or one-size-fits-all compression, are suboptimal. Our findings further reveal that data samples exhibit varying sensitivities to compression, supporting the feasibility of a sample-wise adaptive compression strategy. These insights provide a foundation for developing a new class of storage-aware learning systems. The primary contribution of this work is the systematic characterization of this under-explored challenge, offering valuable insights that advance the understanding of storage-aware learning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。