Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments
For IoT systems using MLaaS, this work offers a more efficient adaptive composition method, though improvements are incremental.
The paper addresses the challenge of maintaining MLaaS composition effectiveness in dynamic IoT environments. The proposed test-time adaptive composition framework reduces computational time compared to traditional methods.
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.