# SuperFedNAS: Cost-Efficient Federated Neural Architecture Search for On-Device Inference

arXiv: https://arxiv.org/abs/2301.10879 · HTML: https://mlsanity.com/paper/2301.10879/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 45 references that are in the map.
- First posted on arXiv 26 Jan 2023.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Federated Optimization in Heterogeneous Networks](https://mlsanity.com/paper/1812.06127/) (2018)
- [An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling](https://mlsanity.com/paper/1803.01271/) (2018)
- [Federated Learning: Strategies for Improving Communication Efficiency](https://mlsanity.com/paper/1610.05492/) (2016)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [LEAF: A Benchmark for Federated Settings](https://mlsanity.com/paper/1812.01097/) (2018)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Ensemble Distillation for Robust Model Fusion in Federated Learning](https://mlsanity.com/paper/2006.07242/) (2020)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [Federated Learning for Mobile Keyboard Prediction](https://mlsanity.com/paper/1811.03604/) (2018)
- [Federated Learning with Matched Averaging](https://mlsanity.com/paper/2002.06440/) (2020)
- [Federated Learning Based on Dynamic Regularization](https://mlsanity.com/paper/2111.04263/) (2021)
- [Progressive Neural Architecture Search](https://mlsanity.com/paper/1712.00559/) (2017)
- [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.03443/) (2018)
- [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://mlsanity.com/paper/2004.02984/) (2020)
- [HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients](https://mlsanity.com/paper/2010.01264/) (2020)
- [Slimmable Neural Networks](https://mlsanity.com/paper/1812.08928/) (2018)
- [Universally Slimmable Networks and Improved Training Techniques](https://mlsanity.com/paper/1903.05134/) (2019)
- [Personalized Federated Learning using Hypernetworks](https://mlsanity.com/paper/2103.04628/) (2021)
- [Don't Use Large Mini-Batches, Use Local SGD](https://mlsanity.com/paper/1808.07217/) (2018)
- [BigNAS: Scaling Up Neural Architecture Search with Big Single-Stage Models](https://mlsanity.com/paper/2003.11142/) (2020)
- [Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System](https://mlsanity.com/paper/1901.09888/) (2019)
- [Patient Clustering Improves Efficiency of Federated Machine Learning to predict mortality and hospital stay time using distributed Electronic Medical Records](https://mlsanity.com/paper/1903.09296/) (2019)
- [NestDNN: Resource-Aware Multi-Tenant On-Device Deep Learning for Continuous Mobile Vision](https://mlsanity.com/paper/1810.10090/) (2018)
- [Federated Learning in Distributed Medical Databases: Meta-Analysis of Large-Scale Subcortical Brain Data](https://mlsanity.com/paper/1810.08553/) (2018)
- [CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment](https://mlsanity.com/paper/2104.12642/) (2021)

## Built on by (most cited first, 4 of 4)

- [FLuID: Mitigating Stragglers in Federated Learning using Invariant Dropout](https://mlsanity.com/paper/2307.02623/) (2023)
- [DeepFedNAS: Efficient Hardware-Aware Architecture Adaptation for Heterogeneous IoT Federations via Pareto-Guided Supernet Training](https://mlsanity.com/paper/2601.15127/) (2026)
- [KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffs](https://mlsanity.com/paper/2605.29259/) (2026)
- [vFedProtoQNAS: Prototype-Guided Personalized Quantum Neural Architecture Search for Virtual Federated Learning](https://mlsanity.com/paper/2610.01718/) (2026)

## Abstract (arXiv)

Neural Architecture Search (NAS) for Federated Learning (FL) is an emerging field. It automates the design and training of Deep Neural Networks (DNNs) when data cannot be centralized due to privacy, communication costs, or regulatory restrictions. Recent federated NAS methods not only reduce manual effort but also help achieve higher accuracy than traditional FL methods like FedAvg. Despite the success, existing federated NAS methods still fall short in satisfying diverse deployment targets common in on-device inference like hardware, latency budgets, or variable battery levels. Most federated NAS methods search for only a limited range of neuro-architectural patterns, repeat them in a DNN, thereby restricting achievable performance. Moreover, these methods incur prohibitive training costs to satisfy deployment targets. They perform the training and search of DNN architectures repeatedly for each case. SuperFedNAS addresses these challenges by decoupling the training and search in federated NAS. SuperFedNAS co-trains a large number of diverse DNN architectures contained inside one supernet in the FL setting. Post-training, clients perform NAS locally to find specialized DNNs by extracting different parts of the trained supernet with no additional training. SuperFedNAS takes O(1) (instead of O(N)) cost to find specialized DNN architectures in FL for any N deployment targets. As part of SuperFedNAS, we introduce MaxNet - a novel FL training algorithm that performs multi-objective federated optimization of a large number of DNN architectures (≈ 5*108) under different client data distributions. Overall, SuperFedNAS achieves upto 37.7% higher accuracy for the same MACs or upto 8.13x reduction in MACs for the same accuracy than existing federated NAS methods.