Adaptive Retrieval Strategies for Context-Aware ML Workflow Synthesis on Resource-Constrained Edge Devices
Main Article Content
Abstract
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.
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
All articles published in the Journal of the Artificial Intelligence Engineers Consortium (JAIEC) are licensed under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
This license permits unrestricted use, distribution, reproduction, and adaptation in any medium, provided the original author(s) and source are properly credited.
Authors retain copyright of their work while granting the journal the right of first publication.
References
Teng, D., Rhee, M., Qin, Y., Zi, B., & Liu, W. (2026). SW-SpeedDLM: Sliding-Window Speculative Decoding for Diffusion Language Models under Long-Context Constraints. Mathematics
Zhang, F., Guo, Z., Ding, J., Yang, J., & Liu, W. (2026). Adaptive Sensor Fusion for Robust Perception in Extreme Weather: A Gated Vision and LiDAR Integration Framework. Sensors
Murshed, M. S., Murphy, C., Hou, D., Khan, N., Ananthanarayanan, G., & Hussain, F. (2021). Machine learning at the network edge: A survey. ACM Computing Surveys (CSUR), 54(8), 1-37.
Warden, P., & Situnayake, D. (2019). Tinyml: Machine learning with tensorflow lite on arduino and ultra-low-power microcontrollers. O'Reilly Media.
Real, E., Aggarwal, A., Huang, Y., & Le, Q. V. (2019, July). Regularized evolution for image classifier architecture search. In Proceedings of the aaai conference on artificial intelligence (Vol. 33, No. 01, pp. 4780-4789).
Ding, G., Yang, S., Lin, H., Chen, Z., & Yang, J. S. (2026). LLM-driven adaptive cloud resource scheduling: Bridging reasoning intelligence with optimization guarantees. IEEE Open Journal of the Computer Society.
Lewis, P., Perez, E., Piktus, A., Petroni, F., Karpukhin, V., Goyal, N., ... & Kiela, D. (2020). Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems, 33, 9459-9474.
Xu, D., Li, T., Li, Y., Su, X., Tarkoma, S., Jiang, T., ... & Hui, P. (2021). Edge intelligence: Empowering intelligence to the edge of network. Proceedings of the IEEE, 109(11), 1778-1837.
Banbury, C., Reddi, V. J., Torelli, P., Holleman, J., Jeffries, N., Kiraly, C., ... & Xuesong, X. (2021). Mlperf tiny benchmark. arXiv preprint arXiv:2106.07597.
Deng, L., Li, G., Han, S., Shi, L., & Xie, Y. (2020). Model compression and hardware acceleration for neural networks: A comprehensive survey. Proceedings of the IEEE, 108(4), 485-532.
Gou, J., Yu, B., Maybank, S. J., & Tao, D. (2021). Knowledge distillation: A survey. International journal of computer vision, 129(6), 1789-1819.
Hadidi, R., Cao, J., Xie, Y., Asgari, B., Krishna, T., & Kim, H. (2019, November). Characterizing the deployment of deep neural networks on commercial edge devices. In 2019 IEEE International Symposium on Workload Characterization (IISWC) (pp. 35-48). IEEE.
Wang, X., Han, Y., Leung, V. C., Niyato, D., Yan, X., & Chen, X. (2020). Convergence of edge computing and deep learning: A comprehensive survey. IEEE communications surveys & tutorials, 22(2), 869-904.
Tan, M., & Le, Q. (2019, May). Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning (pp. 6105-6114). PMLR.
Howard, A., Sandler, M., Chu, G., Chen, L. C., Chen, B., Tan, M., ... & Adam, H. (2019). Searching for mobilenetv3. In Proceedings of the IEEE/CVF international conference on computer vision (pp. 1314-1324).
Wan, A., Dai, X., Zhang, P., He, Z., Tian, Y., Xie, S., ... & Gonzalez, J. E. (2020). Fbnetv2: Differentiable neural architecture search for spatial and channel dimensions. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (pp. 12965-12974).
Lin, J., Zhu, L., Chen, W. M., Wang, W. C., Gan, C., & Han, S. (2022). On-device training under 256kb memory. Advances in Neural Information Processing Systems, 35, 22941-22954.
Zhao, W., Chen, T., Yang, J. S., & Qiu, L. (2026). AutoML-Pipeline: A RAG-enhanced code generation framework with pre-validation for cloud-native machine learning workflows. IEEE Access.
He, X., Zhao, K., & Chu, X. (2021). AutoML: A survey of the state-of-the-art. Knowledge-based systems, 212, 106622.
Ren, P., Xiao, Y., Chang, X., Huang, P. Y., Li, Z., Chen, X., & Wang, X. (2021). A comprehensive survey of neural architecture search: Challenges and solutions. ACM Computing Surveys (CSUR), 54(4), 1-34.
Guo, Z., Zhang, X., Mu, H., Heng, W., Liu, Z., Wei, Y., & Sun, J. (2020, August). Single path one-shot neural architecture search with uniform sampling. In European conference on computer vision (pp. 544-560). Cham: Springer International Publishing.
Liberis, E., Dudziak, Ł., & Lane, N. D. (2021, April). μnas: Constrained neural architecture search for microcontrollers. In Proceedings of the 1st Workshop on Machine Learning and Systems (pp. 70-79).
Fedorov, I., Adams, R. P., Mattina, M., & Whatmough, P. (2019). Sparse: Sparse architecture search for cnns on resource-constrained microcontrollers. Advances in Neural Information Processing Systems, 32.
Karpukhin, V., Oguz, B., Min, S., Lewis, P., Wu, L., Edunov, S., ... & Yih, W. T. (2020, November). Dense passage retrieval for open-domain question answering. In Proceedings of the 2020 conference on empirical methods in natural language processing (EMNLP) (pp. 6769-6781).
Qiu, L. (2025). Reinforcement Learning Approaches for Intelligent Control of Smart Building Energy Systems with Real-Time Adaptation to Occupant Behavior and Weather Conditions. Journal of Computing and Electronic Information Management, 18(2), 32-37.
Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019, June). Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies, volume 1 (long and short papers) (pp. 4171-4186).
Li, T., Sahu, A. K., Zaheer, M., Sanjabi, M., Talwalkar, A., & Smith, V. (2020). Federated optimization in heterogeneous networks. Proceedings of Machine learning and systems, 2, 429-450.
Kairouz, P., & McMahan, H. B. (2021). Advances and open problems in federated learning. Foundations and trends in machine learning, 14(1-2), 1-210.
Chen, J., Liu, J., Liang, Y., & Zhou, M. (2026). KE-MLLM: A Knowledge-Enhanced Multi-Sensor Learning Framework for Explainable Fake Review Detection. Applied Sciences, 16(6), 2909.