提出测试时自适应框架，让物联网中的机器学习服务动态保持高效可用。
Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments
- 测试时动态调整服务，不替换整体流程
- 实测计算时间显著低于传统方法
- 适合资源受限的物联网场景
物联网环境的动态特性影响了机器学习即服务（MLaaS）组合的长期有效性。现有自适应组合方法主要依赖服务替换或重新组合，但寻找合适替代品困难且耗时。为此，我们提出一种针对物联网环境中MLaaS的测试时自适应（TTA）组合框架。首先，引入一种考虑TTA的可组合性模型，以判断适配后的服务是否仍与原有组合兼容；其次，设计服务级自适应模型，在推理过程中调整单个服务，同时保持组合性能。实验结果表明，所提框架在降低计算时间方面优于传统自适应方法。
原文摘要 · Abstract (English)
The dynamic nature of Internet of Things (IoT) environments affects the long-term effectiveness of Machine Learning as a Service (MLaaS) compositions. Existing adaptive composition methods are mainly based on service replacement or re-composition, where identifying suitable substitutes is difficult and time-consuming. To address this, we propose a novel Test-Time Adaptive (TTA) composition framework for MLaaS in IoT environments. First, we introduce a TTA-aware composability model to determine whether adapted services remain compatible with the existing composition. Next, we design a service-level adaptation model to adjust individual services during inference while preserving composition performance. Experimental results demonstrate that the proposed framework reduces computational time more effectively than traditional adaptive approaches.
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。