# AttentiveNAS: Improving Neural Architecture Search via Attentive Sampling

arXiv: https://arxiv.org/abs/2011.09011 · HTML: https://mlsanity.com/paper/2011.09011/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Nov 2020.

## Built on by (most cited first, 30 of 66)

- [A Survey of Quantization Methods for Efficient Neural Network Inference](https://mlsanity.com/paper/2103.13630/) (2021)
- [Neural Prompt Search](https://mlsanity.com/paper/2206.04673/) (2022)
- [Searching the Search Space of Vision Transformer](https://mlsanity.com/paper/2111.14725/) (2021)
- [AlphaNet: Improved Training of Supernets with Alpha-Divergence](https://mlsanity.com/paper/2102.07954/) (2021)
- [Weight subcloning: direct initialization of transformers using larger pretrained ones](https://mlsanity.com/paper/2312.09299/) (2023)
- [CompOFA: Compound Once-For-All Networks for Faster Multi-Platform Deployment](https://mlsanity.com/paper/2104.12642/) (2021)
- [UniNet: Unified Architecture Search with Convolution, Transformer, and MLP](https://mlsanity.com/paper/2110.04035/) (2021)
- [Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond](https://mlsanity.com/paper/2501.10945/) (2025)
- [Latency-Aware Neural Architecture Search with Multi-Objective Bayesian Optimization](https://mlsanity.com/paper/2106.11890/) (2021)
- [SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems](https://mlsanity.com/paper/2204.04705/) (2022)
- [HADAS: Hardware-Aware Dynamic Neural Architecture Search for Edge Performance Scaling](https://mlsanity.com/paper/2212.03354/) (2022)
- [Retraining-free Model Quantization via One-Shot Weight-Coupling Learning](https://mlsanity.com/paper/2401.01543/) (2024)
- [AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment](https://mlsanity.com/paper/2411.10606/) (2024)
- [MKQ-BERT: Quantized BERT with 4-bits Weights and Activations](https://mlsanity.com/paper/2203.13483/) (2022)
- [ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices](https://mlsanity.com/paper/2303.09730/) (2023)
- [EQ-Net: Elastic Quantization Neural Networks](https://mlsanity.com/paper/2308.07650/) (2023)
- [HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models](https://mlsanity.com/paper/2405.10299/) (2024)
- [PRANCE: Joint Token-Optimization and Structural Channel-Pruning for Adaptive ViT Inference](https://mlsanity.com/paper/2407.05010/) (2024)
- [Reconsidering CO2 emissions from Computer Vision](https://mlsanity.com/paper/2104.08702/) (2021)
- [Stitched ViTs are Flexible Vision Backbones](https://mlsanity.com/paper/2307.00154/) (2023)
- [GP-NAS-ensemble: a model for NAS Performance Prediction](https://mlsanity.com/paper/2301.09231/) (2023)
- [SuperShaper: Task-Agnostic Super Pre-training of BERT Models with Variable Hidden Dimensions](https://mlsanity.com/paper/2110.04711/) (2021)
- [Generalized Global Ranking-Aware Neural Architecture Ranker for Efficient Image Classifier Search](https://mlsanity.com/paper/2201.12725/) (2022)
- [FocusFormer: Focusing on What We Need via Architecture Sampler](https://mlsanity.com/paper/2208.10861/) (2022)
- [DetOFA: Efficient Training of Once-for-All Networks for Object Detection Using Path Filter](https://mlsanity.com/paper/2303.13121/) (2023)
- [Efficiently Distilling LLMs for Edge Applications](https://mlsanity.com/paper/2404.01353/) (2024)
- [Structural Pruning of Pre-trained Language Models via Neural Architecture Search](https://mlsanity.com/paper/2405.02267/) (2024)
- [Supernet Training for Federated Image Classification under System Heterogeneity](https://mlsanity.com/paper/2206.01366/) (2022)
- [ObfuNAS: A Neural Architecture Search-based DNN Obfuscation Approach](https://mlsanity.com/paper/2208.08569/) (2022)
- [SwiftPruner: Reinforced Evolutionary Pruning for Efficient Ad Relevance](https://mlsanity.com/paper/2209.00625/) (2022)

## Abstract (arXiv)

Neural architecture search (NAS) has shown great promise in designing state-of-the-art (SOTA) models that are both accurate and efficient. Recently, two-stage NAS, e.g. BigNAS, decouples the model training and searching process and achieves remarkable search efficiency and accuracy. Two-stage NAS requires sampling from the search space during training, which directly impacts the accuracy of the final searched models. While uniform sampling has been widely used for its simplicity, it is agnostic of the model performance Pareto front, which is the main focus in the search process, and thus, misses opportunities to further improve the model accuracy. In this work, we propose AttentiveNAS that focuses on improving the sampling strategy to achieve better performance Pareto. We also propose algorithms to efficiently and effectively identify the networks on the Pareto during training. Without extra re-training or post-processing, we can simultaneously obtain a large number of networks across a wide range of FLOPs. Our discovered model family, AttentiveNAS models, achieves top-1 accuracy from 77.3% to 80.7% on ImageNet, and outperforms SOTA models, including BigNAS and Once-for-All networks. We also achieve ImageNet accuracy of 80.1% with only 491 MFLOPs. Our training code and pretrained models are available at https://github.com/facebookresearch/AttentiveNAS.