EdgeCraft：面向边缘物联网的自动化模型构建
EdgeCraft: Automated Model Crafting for Edge IoT
查看机构详情
- The Chinese University of Hong Kong（香港中文大学）
- Peking University（北京大学）
机构由 AI 辅助整理，请以论文原文为准。
浏览论文内容
中文总结 AI 辅助
EdgeCraft是一个LLM驱动的系统，通过约束感知合成树和多保真度验证器，将高层意图转化为满足动态SLO的可部署边缘ML工件，在50个公共任务中多数超越参考基线。
中文摘要 AI 辅助
机器学习（ML）日益为边缘端的物联网（IoT）应用提供动力。然而，为特定场景生成可部署的边缘ML工件，需要在涵盖数据表示、模型设计、基于领域数据的训练以及运行时定制等巨大搜索空间中进行导航。这一工作流程是碎片化的，且难以在多样化的边缘应用中扩展。我们提出了EdgeCraft，一个由LLM驱动的系统，能将高层意图转化为可部署的边缘ML工件。构建这样一个系统面临两个挑战：（1）如何引导LLM找到满足任务质量、延迟和能量等动态SLO的高质量解决方案？（2）如何以低成本获得可信的目标设备验证？EdgeCraft通过两种设计应对这些挑战。（1）一个约束感知的合成树探索替代候选方案，并利用测量的SLO差距来指导每次改进。（2）一个多保真度验证器逐步将低成本检查与完整的目标设备验证相结合，以降低验证成本，同时保持可靠的验证结果。它还记录已验证的失败以供复用，避免重复的设备工作。为支持并发，EdgeCraft提供了一个多租户运行时，并行运行云端训练和目标设备验证，同时隔离请求。在50个公共任务中，EdgeCraft在40个任务上的最佳观测质量超过了特定任务的参考基线，并在45个任务上找到了满足SLO的工件，其中38个任务上这两个结果重叠。此外，EdgeCraft在我们自行收集的SEN数据集上取得了有竞争力的性能，表明其泛化到真实世界物联网感知任务的能力。
英文摘要
Machine learning (ML) increasingly powers Internet of Things (IoT) applications at the edge. Yet producing a deployable edge ML artifact for a specific scenario requires navigating a huge search space spanning data representation, model design, training on domain-specific data, and runtime customization. This workflow is fragmented and difficult to scale across diverse edge applications. We present EdgeCraft, an LLM-driven system that turns high-level intent into deployable edge ML artifacts. Building such a system raises two challenges: (1) How can an LLM be guided to find high-quality solutions that meet dynamic SLOs for task quality, latency, and energy? (2) How can trustworthy target-device verification be obtained at low cost? EdgeCraft addresses these challenges with two designs. (1) A constraint-aware synthesis tree explores alternative candidates and uses measured SLO gaps to guide each improvement. (2) A multi-fidelity verifier progressively combines low-cost checks with full target-device verification to reduce verification cost while preserving reliable verification results. It also records verified failures for reuse, avoiding repeated device work. To support concurrency, EdgeCraft provides a multi-tenant runtime that runs cloud training and target-device verification in parallel while isolating requests. Across 50 public tasks, EdgeCraft exceeds the task-specific Reference in best-observed quality on 40 tasks and finds an SLO-feasible artifact on 45, with the two outcomes overlapping on 38 tasks. Moreover, EdgeCraft achieves competitive performance on our self-collected SEN dataset, suggesting its generalizability to real-world IoT sensing tasks.
