用压缩特征空间的方法让大模型在普通显卡上高效运行
User-friendly Foundation Model Adapters for Multivariate Time Series Classification
- 用主成分分析和神经网络适配器降低时间序列维度
- 压缩到原大小2.10%仍保持96.15%准确率，提速10倍
- 适合资源有限但想用大模型的开发者和研究者
基础模型虽有效，但对计算资源要求高。本文探索降维技术，使用户能在标准GPU上运行大型预训练模型而不损失性能。通过主成分分析与基于神经网络的适配器，降低多变量时间序列数据维度，同时保留关键特征。实验显示，相比基线模型最高提速10倍，单卡可容纳数据集数量最多提升4.5倍，且将潜在空间压缩至原始大小的2.10%时，分类准确率仍保持在96.15%。该方法为更易用、可扩展的基础模型提供可能。
原文摘要 · Abstract (English)
Foundation models, while highly effective, are often resource-intensive, requiring substantial inference time and memory. This paper addresses the challenge of making these models more accessible with limited computational resources by exploring dimensionality reduction techniques. Our goal is to enable users to run large pre-trained foundation models on standard GPUs without sacrificing performance. We investigate classical methods such as Principal Component Analysis alongside neural network-based adapters, aiming to reduce the dimensionality of multivariate time series data while preserving key features. Our experiments show up to a 10x speedup compared to the baseline model, without performance degradation, and enable up to 4.5x more datasets to fit on a single GPU, paving the way for more user-friendly and scalable foundation models.
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。