# OrchNAS: Orchestrated Neural Architecture Search Service for Personalised Federated Edge Intelligence

arXiv: https://arxiv.org/abs/2607.22805 · HTML: https://mlsanity.com/paper/2607.22805/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 34 references that are in the map.
- First posted on arXiv 24 Jul 2026.

## Builds on (most cited first, 9 of 9)

- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Random Search and Reproducibility for Neural Architecture Search](https://mlsanity.com/paper/1902.07638/) (2019)
- [FLaaS: Federated Learning as a Service](https://mlsanity.com/paper/2011.09359/) (2020)
- [SPIDER: Searching Personalized Neural Architecture for Federated Learning](https://mlsanity.com/paper/2112.13939/) (2021)
- [A Survey on UAV-enabled Edge Computing: Resource Management Perspective](https://mlsanity.com/paper/2210.06679/) (2022)
- [Long-term IaaS Provider Selection using Short-term Trial Experience](https://mlsanity.com/paper/2102.12222/) (2021)
- [Reinforcement Learning Controlled Adaptive PSO for Task Offloading in IIoT Edge Computing](https://mlsanity.com/paper/2501.15203/) (2025)

## Abstract (arXiv)

We propose OrchNAS, an energy-aware, personalised, federated edge intelligence framework that leverages a Neural Architecture Search Service to automatically design service-adaptive models for heterogeneous edge environments. The framework orchestrates the architecture search process on a server-side NAS service, enabling edge services to derive personalised architectures under device-level energy, computation, and memory constraints. We introduce an energy-aware global architecture search mechanism that learns a compact global representation across heterogeneous services. We develop an energy-efficient architecture selection mechanism that enables each service to derive a personalised subnet that satisfies its resource constraints via a progressive, greedy, energy-aware pruning strategy. We propose an energy-efficient personalised model optimisation scheme that updates service-adaptive parameters while preserving global representations, where a primal-dual optimisation mechanism enforces strict energy budgets during architecture adaptation. Experiments on real-world and benchmark datasets demonstrate the effectiveness of the proposed approach.