为物联网设备推荐适配的预训练模型，兼顾任务性能与硬件限制。
Recommending Pre-Trained Models for IoT Devices
- 提出基于硬件约束的预训练模型推荐方法，评估模型在设备上的实际表现。
- 相较现有方法显著提升模型在资源受限设备上的部署成功率。
- 适合边缘计算、嵌入式AI开发人员参考使用。
预训练模型（PTM）的普及使得机器学习应用部署更快速，减少了对大规模训练的需求。量化和压缩等技术进一步拓展了其在资源受限的物联网（IoT）设备上的适用性。然而，面对同一任务下众多可选的预训练模型，工程师往往难以高效评估每个模型的适用性。尽管已有方法如LogME、LEEP和ModelSpider可通过无须大量调优的方式估计模型的任务相关性，但这些方法大多忽略硬件约束——这在物联网场景中是关键短板。本文揭示了现有模型推荐方法在硬件适应性方面的局限，并提出一种新型的、考虑硬件约束的预训练模型选择方法。同时，本文还提出一个研究议程，以推动面向物联网应用的高效、硬件感知型模型推荐系统的发展。
原文摘要 · Abstract (English)
The availability of pre-trained models (PTMs) has enabled faster deployment of machine learning across applications by reducing the need for extensive training. Techniques like quantization and distillation have further expanded PTM applicability to resource-constrained IoT hardware. Given the many PTM options for any given task, engineers often find it too costly to evaluate each model's suitability. Approaches such as LogME, LEEP, and ModelSpider help streamline model selection by estimating task relevance without exhaustive tuning. However, these methods largely leave hardware constraints as future work-a significant limitation in IoT settings. In this paper, we identify the limitations of current model recommendation approaches regarding hardware constraints and introduce a novel, hardware-aware method for PTM selection. We also propose a research agenda to guide the development of effective, hardware-conscious model recommendation systems for IoT applications.
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。