# Breaking the Curse of Space Explosion: Towards Efficient NAS with Curriculum Search

arXiv: https://arxiv.org/abs/2007.07197 · HTML: https://mlsanity.com/paper/2007.07197/

## Key facts

- Cited by 33 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jul 2020.

## Built on by (most cited first, 30 of 33)

- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [BungeeNeRF: Progressive Neural Radiance Field for Extreme Multi-scale Scene Rendering](https://mlsanity.com/paper/2112.05504/) (2021)
- [TransNAS-Bench-101: Improving Transferability and Generalizability of Cross-Task Neural Architecture Search](https://mlsanity.com/paper/2105.11871/) (2021)
- [Neural Feature Search for RGB-Infrared Person Re-Identification](https://mlsanity.com/paper/2104.02366/) (2021)
- [Contrastive Neural Architecture Search with Neural Architecture Comparators](https://mlsanity.com/paper/2103.05471/) (2021)
- [Sharpness-aware Quantization for Deep Neural Networks](https://mlsanity.com/paper/2111.12273/) (2021)
- [Towards Accurate and Compact Architectures via Neural Architecture Transformer](https://mlsanity.com/paper/2102.10301/) (2021)
- [Step-On-Feet Tuning: Scaling Self-Alignment of LLMs via Bootstrapping](https://mlsanity.com/paper/2402.07610/) (2024)
- [Improving Robustness by Enhancing Weak Subnets](https://mlsanity.com/paper/2201.12765/) (2022)
- [AdaXpert: Adapting Neural Architecture for Growing Data](https://mlsanity.com/paper/2107.00254/) (2021)
- [When Do Curricula Work in Federated Learning?](https://mlsanity.com/paper/2212.12712/) (2022)
- [Downscaled Representation Matters: Improving Image Rescaling with Collaborative Downscaled Images](https://mlsanity.com/paper/2211.10643/) (2022)
- [CLOSE: Curriculum Learning On the Sharing Extent Towards Better One-shot NAS](https://mlsanity.com/paper/2207.07868/) (2022)
- [DiscrimLoss: A Universal Loss for Hard Samples and Incorrect Samples Discrimination](https://mlsanity.com/paper/2208.09884/) (2022)
- [FocusFormer: Focusing on What We Need via Architecture Sampler](https://mlsanity.com/paper/2208.10861/) (2022)
- [Boosting Semi-Supervised Learning with Contrastive Complementary Labeling](https://mlsanity.com/paper/2212.06643/) (2022)
- [Accelerating Training Speed of Tiny Recursive Models with Curriculum Guided Adaptive Recursion](https://mlsanity.com/paper/2511.08653/) (2025)
- [Pareto-aware Neural Architecture Generation for Diverse Computational Budgets](https://mlsanity.com/paper/2210.07634/) (2022)
- [Modular Machine Learning: An Indispensable Path towards New-Generation Large Language Models](https://mlsanity.com/paper/2504.20020/) (2025)
- [Pareto-Frontier-aware Neural Architecture Generation for Diverse Budgets](https://mlsanity.com/paper/2103.00219/) (2021)
- [Automated Dominative Subspace Mining for Efficient Neural Architecture Search](https://mlsanity.com/paper/2210.17180/) (2022)
- [Enhancing Spatio-temporal Quantile Forecasting with Curriculum Learning: Lessons Learned](https://mlsanity.com/paper/2406.12709/) (2024)
- [Layer-Aware Influence for Online Data Valuation Estimation](https://mlsanity.com/paper/2510.16007/) (2025)
- [AutoTS: Automatic Time Series Forecasting Model Design Based on Two-Stage Pruning](https://mlsanity.com/paper/2203.14169/) (2022)
- [DARTSRepair: Core-failure-set Guided DARTS for Network Robustness to Common Corruptions](https://mlsanity.com/paper/2209.10381/) (2022)
- [Neural Architecture Retrieval](https://mlsanity.com/paper/2307.07919/) (2023)
- [One Search Fits All: Pareto-Optimal Eco-Friendly Model Selection](https://mlsanity.com/paper/2505.01468/) (2025)
- [DDS-NAS: Dynamic Data Selection within Neural Architecture Search via On-line Hard Example Mining applied to Image Classification](https://mlsanity.com/paper/2506.14667/) (2025)
- [CIMNAS: A Joint Framework for Compute-In-Memory-Aware Neural Architecture Search](https://mlsanity.com/paper/2509.25862/) (2025)
- [Curriculum generation using Autoencoder based continuous optimization](https://mlsanity.com/paper/2106.08569/) (2021)

## Abstract (arXiv)

Neural architecture search (NAS) has become an important approach to automatically find effective architectures. To cover all possible good architectures, we need to search in an extremely large search space with billions of candidate architectures. More critically, given a large search space, we may face a very challenging issue of space explosion. However, due to the limitation of computational resources, we can only sample a very small proportion of the architectures, which provides insufficient information for the training. As a result, existing methods may often produce suboptimal architectures. To alleviate this issue, we propose a curriculum search method that starts from a small search space and gradually incorporates the learned knowledge to guide the search in a large space. With the proposed search strategy, our Curriculum Neural Architecture Search (CNAS) method significantly improves the search efficiency and finds better architectures than existing NAS methods. Extensive experiments on CIFAR-10 and ImageNet demonstrate the effectiveness of the proposed method.