# Memory-Optimized Once-For-All Network

arXiv: https://arxiv.org/abs/2409.05900 · HTML: https://mlsanity.com/paper/2409.05900/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 23 references that are in the map.
- First posted on arXiv 5 Sep 2024.

## Builds on (most cited first, 14 of 14)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [Random Search and Reproducibility for Neural Architecture Search](https://mlsanity.com/paper/1902.07638/) (2019)
- [Deep Learning is Robust to Massive Label Noise](https://mlsanity.com/paper/1705.10694/) (2017)
- [Efficient Multi-objective Neural Architecture Search via Lamarckian Evolution](https://mlsanity.com/paper/1804.09081/) (2018)
- [CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment](https://mlsanity.com/paper/2104.12642/) (2021)
- [Analysis of Generalizability of Deep Neural Networks Based on the Complexity of Decision Boundary](https://mlsanity.com/paper/2009.07974/) (2020)
- [To update or not to update? Neurons at equilibrium in deep models](https://mlsanity.com/paper/2207.09455/) (2022)
- [DetOFA: Efficient Training of Once-for-All Networks for Object Detection Using Path Filter](https://mlsanity.com/paper/2303.13121/) (2023)
- [Transfer-Once-For-All: AI Model Optimization for Edge](https://mlsanity.com/paper/2303.15485/) (2023)

## Built on by (most cited first, 1 of 1)

- [ProARD: progressive adversarial robustness distillation: provide wide range of robust students](https://mlsanity.com/paper/2506.07666/) (2025)

## Abstract (arXiv)

Deploying Deep Neural Networks (DNNs) on different hardware platforms is challenging due to varying resource constraints. Besides handcrafted approaches aiming at making deep models hardware-friendly, Neural Architectures Search is rising as a toolbox to craft more efficient DNNs without sacrificing performance. Among these, the Once-For-All (OFA) approach offers a solution by allowing the sampling of well-performing sub-networks from a single supernet -- this leads to evident advantages in terms of computation. However, OFA does not fully utilize the potential memory capacity of the target device, focusing instead on limiting maximum memory usage per layer. This leaves room for an unexploited potential in terms of model generalizability. In this paper, we introduce a Memory-Optimized OFA (MOOFA) supernet, designed to enhance DNN deployment on resource-limited devices by maximizing memory usage (and for instance, features diversity) across different configurations. Tested on ImageNet, our MOOFA supernet demonstrates improvements in memory exploitation and model accuracy compared to the original OFA supernet. Our code is available at https://github.com/MaximeGirard/memory-optimized-once-for-all.