# Prioritized Architecture Sampling with Monto-Carlo Tree Search

arXiv: https://arxiv.org/abs/2103.11922 · HTML: https://mlsanity.com/paper/2103.11922/

## Key facts

- Cited by 32 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 40 references that are in the map.
- First posted on arXiv 22 Mar 2021.

## Builds on (most cited first, 28 of 28)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [Transformer in Transformer](https://mlsanity.com/paper/2103.00112/) (2021)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [GhostNet: More Features from Cheap Operations](https://mlsanity.com/paper/1911.11907/) (2019)
- [PPDM: Parallel Point Detection and Matching for Real-time Human-Object Interaction Detection](https://mlsanity.com/paper/1912.12898/) (2019)
- [FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search](https://mlsanity.com/paper/1907.01845/) (2019)
- [Learning Search Space Partition for Black-box Optimization using Monte Carlo Tree Search](https://mlsanity.com/paper/2007.00708/) (2020)
- [SGAS: Sequential Greedy Architecture Search](https://mlsanity.com/paper/1912.00195/) (2019)
- [GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet](https://mlsanity.com/paper/2003.11236/) (2020)
- [BayesNAS: A Bayesian Approach for Neural Architecture Search](https://mlsanity.com/paper/1905.04919/) (2019)
- [Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimation](https://mlsanity.com/paper/2007.02846/) (2020)
- [ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse Coding](https://mlsanity.com/paper/2010.06176/) (2020)
- [Hit-Detector: Hierarchical Trinity Architecture Search for Object Detection](https://mlsanity.com/paper/2003.11818/) (2020)
- [DeepArchitect: Automatically Designing and Training Deep Architectures](https://mlsanity.com/paper/1704.08792/) (2017)
- [A Semi-Supervised Assessor of Neural Architectures](https://mlsanity.com/paper/2005.06821/) (2020)
- [Towards Improving the Consistency, Efficiency, and Flexibility of Differentiable Neural Architecture Search](https://mlsanity.com/paper/2101.11342/) (2021)
- [Locally Free Weight Sharing for Network Width Search](https://mlsanity.com/paper/2102.05258/) (2021)
- [Sample-Efficient Neural Architecture Search by Learning Action Space](https://mlsanity.com/paper/1906.06832/) (2019)
- [Neural Architecture Search using Deep Neural Networks and Monte Carlo Tree Search](https://mlsanity.com/paper/1805.07440/) (2018)
- [Powering One-shot Topological NAS with Stabilized Share-parameter Proxy](https://mlsanity.com/paper/2005.10511/) (2020)
- [BETANAS: BalancEd TrAining and selective drop for Neural Architecture Search](https://mlsanity.com/paper/1912.11191/) (2019)

## Built on by (most cited first, 30 of 32)

- [SimMatch: Semi-supervised Learning with Similarity Matching](https://mlsanity.com/paper/2203.06915/) (2022)
- [Can GPT-4 Perform Neural Architecture Search?](https://mlsanity.com/paper/2304.10970/) (2023)
- [Using Large Language Models for Hyperparameter Optimization](https://mlsanity.com/paper/2312.04528/) (2023)
- [LightViT: Towards Light-Weight Convolution-Free Vision Transformers](https://mlsanity.com/paper/2207.05557/) (2022)
- [Evaluation and Improvement of Interpretability for Self-Explainable Part-Prototype Networks](https://mlsanity.com/paper/2212.05946/) (2022)
- [NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy](https://mlsanity.com/paper/2201.13396/) (2022)
- [ViTAS: Vision Transformer Architecture Search](https://mlsanity.com/paper/2106.13700/) (2021)
- [Masked Distillation with Receptive Tokens](https://mlsanity.com/paper/2205.14589/) (2022)
- [K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets](https://mlsanity.com/paper/2106.06442/) (2021)
- [Generic Neural Architecture Search via Regression](https://mlsanity.com/paper/2108.01899/) (2021)
- [Re-mine, Learn and Reason: Exploring the Cross-modal Semantic Correlations for Language-guided HOI detection](https://mlsanity.com/paper/2307.13529/) (2023)
- [GreedyNASv2: Greedier Search with a Greedy Path Filter](https://mlsanity.com/paper/2111.12609/) (2021)
- [DyRep: Bootstrapping Training with Dynamic Re-parameterization](https://mlsanity.com/paper/2203.12868/) (2022)
- [Zero-Cost Operation Scoring in Differentiable Architecture Search](https://mlsanity.com/paper/2106.06799/) (2021)
- [BLOX: Macro Neural Architecture Search Benchmark and Algorithms](https://mlsanity.com/paper/2210.07271/) (2022)
- [DiffNAS: Bootstrapping Diffusion Models by Prompting for Better Architectures](https://mlsanity.com/paper/2310.04750/) (2023)
- [LLaPa: A Vision-Language Model Framework for Counterfactual-Aware Procedural Planning](https://mlsanity.com/paper/2507.08496/) (2025)
- [DetOFA: Efficient Training of Once-for-All Networks for Object Detection Using Path Filter](https://mlsanity.com/paper/2303.13121/) (2023)
- [ScaleNet: Searching for the Model to Scale](https://mlsanity.com/paper/2207.07267/) (2022)
- [Put CASH on Bandits: A Max K-Armed Problem for Automated Machine Learning](https://mlsanity.com/paper/2505.05226/) (2025)
- [Are Neural Architecture Search Benchmarks Well Designed? A Deeper Look Into Operation Importance](https://mlsanity.com/paper/2303.16938/) (2023)
- [OvSW: Overcoming Silent Weights for Accurate Binary Neural Networks](https://mlsanity.com/paper/2407.05257/) (2024)
- [The BUTTER Zone: An Empirical Study of Training Dynamics in Fully Connected Neural Networks](https://mlsanity.com/paper/2207.12547/) (2022)
- [Balanced Mixture of SuperNets for Learning the CNN Pooling Architecture](https://mlsanity.com/paper/2306.11982/) (2023)
- [Conditional super-network weights](https://mlsanity.com/paper/2104.11522/) (2021)
- [WPNAS: Neural Architecture Search by jointly using Weight Sharing and Predictor](https://mlsanity.com/paper/2203.02086/) (2022)
- [Multi-scale alignment and Spatial ROI Module for COVID-19 Diagnosis](https://mlsanity.com/paper/2207.01345/) (2022)
- [Propheter: Prophetic Teacher Guided Long-Tailed Distribution Learning](https://mlsanity.com/paper/2304.04135/) (2023)
- [Dynamic Data Augmentation via MCTS for Prostate MRI Segmentation](https://mlsanity.com/paper/2305.15777/) (2023)
- [Efficacy of Neural Prediction-Based Zero-Shot NAS](https://mlsanity.com/paper/2308.16775/) (2023)

## Abstract (arXiv)

One-shot neural architecture search (NAS) methods significantly reduce the search cost by considering the whole search space as one network, which only needs to be trained once. However, current methods select each operation independently without considering previous layers. Besides, the historical information obtained with huge computation cost is usually used only once and then discarded. In this paper, we introduce a sampling strategy based on Monte Carlo tree search (MCTS) with the search space modeled as a Monte Carlo tree (MCT), which captures the dependency among layers. Furthermore, intermediate results are stored in the MCT for the future decision and a better exploration-exploitation balance. Concretely, MCT is updated using the training loss as a reward to the architecture performance; for accurately evaluating the numerous nodes, we propose node communication and hierarchical node selection methods in the training and search stages, respectively, which make better uses of the operation rewards and hierarchical information. Moreover, for a fair comparison of different NAS methods, we construct an open-source NAS benchmark of a macro search space evaluated on CIFAR-10, namely NAS-Bench-Macro. Extensive experiments on NAS-Bench-Macro and ImageNet demonstrate that our method significantly improves search efficiency and performance. For example, by only searching 20 architectures, our obtained architecture achieves 78.0% top-1 accuracy with 442M FLOPs on ImageNet. Code (Benchmark) is available at: urlhttps://github.com/xiusu/NAS-Bench-Macro.