Zero-Shot, Self-Supervised Neural Architecture Search for Cross-Domain Edge-Cloud Co-Deployment without Human Intervention
DOI:
https://doi.org/10.63282/3050-9246/ICRTCSIT-123Keywords:
Zero-Shot Learning, Self-Supervised Learning, Neural Architecture Search (NAS), Edge-Cloud Co-Deployment, Cross-Domain Adaptation, Automated Machine Learning (AutoML), Hardware-Aware NAS, Latency Optimization, Energy Efficiency, Model Deployment AutomationAbstract
The increasing complexity and scale of edge-cloud systems pose significant challenges for deploying optimized neural network architectures across heterogeneous environments. This paper proposes a novel zero-shot, self-supervised Neural Architecture Search (NAS) framework designed for cross-domain edge-cloud co-deployment, eliminating the need for human intervention. Our approach leverages a self-supervised learning paradigm to evaluate and adapt neural architectures without labeled data, enabling rapid generalization across unseen domains and deployment scenarios. By integrating hardware-aware performance predictors with a zero-shot scoring mechanism, the framework efficiently selects candidate architectures suitable for both edge devices and cloud infrastructures. Extensive experiments demonstrate that our method achieves competitive accuracy, latency, and energy efficiency trade-offs while requiring significantly less computational overhead compared to traditional NAS approaches. This work paves the way toward fully automated, scalable, and domain-agnostic AI model deployment pipelines
Downloads
References
[1] O. Dutta, T. Kanvar, and S. Agarwal, "Search-time Efficient Device Constraints-Aware Neural Architecture Search," 2023. [PDF]
[2] H. Huang, X. Chang, W. Hu, and L. Yao, "MatchNAS: Optimizing Edge AI in Sparse-Label Data Contexts via Automating Deep Neural Network Porting for Mobile Deployment," 2024. [PDF]
[3] Y. Ci, C. Lin, M. Sun, B. Chen et al., "Evolving Search Space for Neural Architecture Search," 2020. [PDF]
[4] A. Cazasnoves, P. A. Ganaye, K. Sanchis, and T. Ceillier, "Neural Architecture Search in operational context: a remote sensing case-study," 2021. [PDF]
[5] G. Li, Y. Yang, K. Bhardwaj, and R. Marculescu, "ZiCo: Zero-shot NAS via Inverse Coefficient of Variation on Gradients," 2023. [PDF]
[6] Y. Qiao, H. Xu, and S. Huang, "TG-NAS: Leveraging Zero-Cost Proxies with Transformer and Graph Convolution Networks for Efficient Neural Architecture Search," 2024. [PDF]
[7] Z. Yang, S. Zhang, R. Li, C. Li et al., "Efficient Resource-Aware Convolutional Neural Architecture Search for Edge Computing with Pareto-Bayesian Optimization," 2021. ncbi.nlm.nih.gov
[8] N. Nguyen and J. Morris Chang, "Contrastive Self-supervised Neural Architecture Search," 2021. [PDF]
[9] S. Jung, J. Lukasik, and M. Keuper, "Neural Architecture Design and Robustness: A Dataset," 2023. [PDF]
[10] Y. Wang, X. Chen, and Q. Wang, "Privacy-preserving Security Inference Towards Cloud-Edge Collaborative Using Differential Privacy," 2022. [PDF]
[11] Kommineni, M., Panyaram, S., Banala, S., Vegineni, G. C., Hullurappa, M., & Sehrawat, S. K. (2025, April). Optimizing Processes and Insights: the Role of Ai Architecture in Corporate Data Management. In 2025 International Conference on Data Science and Business Systems (ICDSBS) (pp. 1-7). IEEE.
[12] Settibathini, V. S., Virmani, A., Kuppam, M., S., N., Manikandan, S., & C., E. (2024). Shedding Light on Dataset Influence for More Transparent Machine Learning. In P. Paramasivan, S. Rajest, K. Chinnusamy, R. Regin, & F. John Joseph (Eds.), Explainable AI Applications for Human Behavior Analysis (pp. 33-48). IGI Global Scientific Publishing. https://doi.org/10.4018/979-8-3693-1355-8.ch003
[13] Teja Thallam, N. S. (2025). AI-Powered Monitoring and Predictive Maintenance for Cloud Infrastructure: Leveraging AWS Cloud Watch and ML. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 6(1), 55-61. https://doi.org/10.63282/3050-9262.IJAIDSML-V6I1P107
[14] Rajender Pell Reddy, "A Survey of Distributed Denial of Service (DDoS) Attack Mitigation Techniques," International Journal of Computer Trends and Technology (IJCTT), vol. 72, no. 12, pp. 69-77, 2024. Crossref, https://doi.org/10.14445/22312803/ IJCTT-V72I12P108
[15] Varinder Kumar Sharma - 5G-Enabled Mission-Critical Networks Design and Performance Analysis -International Journal on Science and Technology (IJSAT) Volume 14, Issue 4, October-December 2023. https://doi.org/10.71097/IJSAT.v14.i4.7998
[16] Kanji, R. K. (2022). Generative Query Optimization in Data Warehousing: A Foundation Model-Based Approach for Autonomous SQL Generation and Execution Optimization in Hybrid Architectures. Available at SSRN 5401216.
[17] Garg, A., Pandey, M., & Pathak, A. R. (2024). A Multi-Layered AI-IoT Framework for Adaptive Financial Services. International Journal of Emerging Trends in Computer Science and Information Technology, 5(3), 47-57. https://doi.org/10.63282/3050-9246.IJETCSIT-V5I3P105
