Adaptive Retrieval Strategies for Context-Aware ML Workflow Synthesis on Resource-Constrained Edge Devices
Journal of the Artificial Intelligence Engineers Consortium · 2026
DOI: 10.66238/jaiec67 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of the Artificial Intelligence Engineers Consortium, 2026. Verfasst von Laura Bennett und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The proliferation of Internet of Things (IoT) devices has created substantial demand for machine learning (ML) pipelines capable of operating under severe computational and memory constraints. This paper presents an adaptive retrieval framework that synthesizes context-aware ML workflows on resource-constrained edge devices by dynamically querying a structured component library in response to real-time device profiling signals. Drawing on a two-phase deployment-and-runtime architecture, the framework encodes available random-access memory (RAM), CPU utilization, and battery state into a compact context vector that drives a multi-stage retrieval procedure progressively filtering and ranking candidate components by feasibility and semantic relevance. The component library is populated primarily with depthwise separable convolution (DSC) operators, which reduce multiply-accumulate (MAC) operations by a factor of eight to nine relative to standard convolutions while preserving representational capacity. Experiments on three embedded platforms demonstrate a 38.4% reduction in pipeline deployment failure rates under memory contention, alongside per-inference energy savings achieved by prioritizing on-chip buffer computation over costly dynamic random-access memory (DRAM) access. The results indicate that framing workflow construction as a retrieval task is substantially more tractable for edge devices than online architecture search, and that context-sensitive query design is the primary source of accuracy retention across varied resource regimes.
Zitieren
APA
Bennett, L., & Morales, K. (2026). Adaptive Retrieval Strategies for Context-Aware ML Workflow Synthesis on Resource-Constrained Edge Devices. Journal of the Artificial Intelligence Engineers Consortium. https://doi.org/10.66238/jaiec67
Vancouver
Bennett L, Morales K. Adaptive Retrieval Strategies for Context-Aware ML Workflow Synthesis on Resource-Constrained Edge Devices. Journal of the Artificial Intelligence Engineers Consortium. 2026. doi:10.66238/jaiec67
BibTeX
@article{Bennett2026,
author = {Bennett, Laura and Morales, Kevin},
title = {Adaptive Retrieval Strategies for Context-Aware ML Workflow Synthesis on Resource-Constrained Edge Devices},
journal = {Journal of the Artificial Intelligence Engineers Consortium},
year = {2026},
doi = {10.66238/jaiec67}
}
EUVIMED