# Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search

arXiv: https://arxiv.org/abs/1901.01074 · HTML: https://mlsanity.com/paper/1901.01074/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jan 2019.

## Built on by (most cited first, 24 of 24)

- [A Comprehensive Survey on Hardware-Aware Neural Architecture Search](https://mlsanity.com/paper/2101.09336/) (2021)
- [Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overview](https://mlsanity.com/paper/2206.07438/) (2022)
- [Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search](https://mlsanity.com/paper/2108.08910/) (2021)
- [Hitchhiker's Guide to Super-Resolution: Introduction and Recent Advances](https://mlsanity.com/paper/2209.13131/) (2022)
- [Efficiently Controlling Multiple Risks with Pareto Testing](https://mlsanity.com/paper/2210.07913/) (2022)
- [Self-Calibrated Efficient Transformer for Lightweight Super-Resolution](https://mlsanity.com/paper/2204.08913/) (2022)
- [Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution](https://mlsanity.com/paper/2207.12577/) (2022)
- [Collapsible Linear Blocks for Super-Efficient Super Resolution](https://mlsanity.com/paper/2103.09404/) (2021)
- [Cross-receptive Focused Inference Network for Lightweight Image Super-Resolution](https://mlsanity.com/paper/2207.02796/) (2022)
- [Multi-conditioned Graph Diffusion for Neural Architecture Search](https://mlsanity.com/paper/2403.06020/) (2024)
- [AMQ: Enabling AutoML for Mixed-precision Weight-Only Quantization of Large Language Models](https://mlsanity.com/paper/2509.12019/) (2025)
- [Online Video Super-Resolution with Convolutional Kernel Bypass Graft](https://mlsanity.com/paper/2208.02470/) (2022)
- [GhostSR: Learning Ghost Features for Efficient Image Super-Resolution](https://mlsanity.com/paper/2101.08525/) (2021)
- [TransNAS-TSAD: Harnessing Transformers for Multi-Objective Neural Architecture Search in Time Series Anomaly Detection](https://mlsanity.com/paper/2311.18061/) (2023)
- [Multi-Objective Hardware Aware Neural Architecture Search using Hardware Cost Diversity](https://mlsanity.com/paper/2404.12403/) (2024)
- [Neural Architecture Search for Image Super-Resolution Using Densely Constructed Search Space: DeCoNAS](https://mlsanity.com/paper/2104.09048/) (2021)
- [GRAN: Ghost Residual Attention Network for Single Image Super Resolution](https://mlsanity.com/paper/2302.14557/) (2023)
- [RAGSR: Regional Attention Guided Diffusion for Image Super-Resolution](https://mlsanity.com/paper/2508.16158/) (2025)
- [Multi-Objective Evolutionary Neural Architecture Search for Recurrent Neural Networks](https://mlsanity.com/paper/2403.11173/) (2024)
- [Bilevel Optimization for Neural Architecture Search](https://mlsanity.com/paper/2606.29582/) (2026)
- [Dextr: Zero-Shot Neural Architecture Search with Singular Value Decomposition and Extrinsic Curvature](https://mlsanity.com/paper/2508.12977/) (2025)
- [A Continuous Encoding-Based Representation for Efficient Multi-Fidelity Multi-Objective Neural Architecture Search](https://mlsanity.com/paper/2509.01943/) (2025)
- [A Survey on Multi-Objective Neural Architecture Search](https://mlsanity.com/paper/2307.09099/) (2023)
- [An Integrated Approach to Neural Architecture Search for Deep Q-Networks](https://mlsanity.com/paper/2510.19872/) (2025)

## Abstract (arXiv)

Fabricating neural models for a wide range of mobile devices demands for a specific design of networks due to highly constrained resources. Both evolution algorithms (EA) and reinforced learning methods (RL) have been dedicated to solve neural architecture search problems. However, these combinations usually concentrate on a single objective such as the error rate of image classification. They also fail to harness the very benefits from both sides. In this paper, we present a new multi-objective oriented algorithm called MoreMNAS (Multi-Objective Reinforced Evolution in Mobile Neural Architecture Search) by leveraging good virtues from both EA and RL. In particular, we incorporate a variant of multi-objective genetic algorithm NSGA-II, in which the search space is composed of various cells so that crossovers and mutations can be performed at the cell level. Moreover, reinforced control is mixed with a natural mutating process to regulate arbitrary mutation, maintaining a delicate balance between exploration and exploitation. Therefore, not only does our method prevent the searched models from degrading during the evolution process, but it also makes better use of learned knowledge. Our experiments conducted in Super-resolution domain (SR) deliver rivalling models compared to some state-of-the-art methods with fewer FLOPS.