Recommending Pre-Trained Models for IoT Devices
This work addresses the challenge for IoT engineers in efficiently choosing suitable models under hardware limitations, but it is incremental as it builds on prior selection techniques.
The paper tackled the problem of selecting pre-trained models for IoT devices by identifying limitations in existing methods that ignore hardware constraints, and introduced a hardware-aware method for model recommendation.
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.