# GreedyNASv2: Greedier Search with a Greedy Path Filter

arXiv: https://arxiv.org/abs/2111.12609 · HTML: https://mlsanity.com/paper/2111.12609/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 42 references that are in the map.
- First posted on arXiv 24 Nov 2021.

## Builds on (most cited first, 30 of 31)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [MMDetection: Open MMLab Detection Toolbox and Benchmark](https://mlsanity.com/paper/1906.07155/) (2019)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Designing Network Design Spaces](https://mlsanity.com/paper/2003.13678/) (2020)
- [Single Path One-Shot Neural Architecture Search with Uniform Sampling](https://mlsanity.com/paper/1904.00420/) (2019)
- [Selective Kernel Networks](https://mlsanity.com/paper/1903.06586/) (2019)
- [ResNet strikes back: An improved training procedure in timm](https://mlsanity.com/paper/2110.00476/) (2021)
- [Positive-Unlabeled Learning with Non-Negative Risk Estimator](https://mlsanity.com/paper/1703.00593/) (2017)
- [FairNAS: Rethinking Evaluation Fairness of Weight Sharing Neural Architecture Search](https://mlsanity.com/paper/1907.01845/) (2019)
- [MixConv: Mixed Depthwise Convolutional Kernels](https://mlsanity.com/paper/1907.09595/) (2019)
- [DetNAS: Backbone Search for Object Detection](https://mlsanity.com/paper/1903.10979/) (2019)
- [GreedyNAS: Towards Fast One-Shot NAS with Greedy Supernet](https://mlsanity.com/paper/2003.11236/) (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)
- [Angle-based Search Space Shrinking for Neural Architecture Search](https://mlsanity.com/paper/2004.13431/) (2020)
- [Prioritized Architecture Sampling with Monto-Carlo Tree Search](https://mlsanity.com/paper/2103.11922/) (2021)
- [ViTAS: Vision Transformer Architecture Search](https://mlsanity.com/paper/2106.13700/) (2021)
- [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)
- [Evolving Search Space for Neural Architecture Search](https://mlsanity.com/paper/2011.10904/) (2020)
- [BCNet: Searching for Network Width with Bilaterally Coupled Network](https://mlsanity.com/paper/2105.10533/) (2021)
- [K-shot NAS: Learnable Weight-Sharing for NAS with K-shot Supernets](https://mlsanity.com/paper/2106.06442/) (2021)

## Built on by (most cited first, 12 of 12)

- [Can GPT-4 Perform Neural Architecture Search?](https://mlsanity.com/paper/2304.10970/) (2023)
- [LightViT: Towards Light-Weight Convolution-Free Vision Transformers](https://mlsanity.com/paper/2207.05557/) (2022)
- [ElasticViT: Conflict-aware Supernet Training for Deploying Fast Vision Transformer on Diverse Mobile Devices](https://mlsanity.com/paper/2303.09730/) (2023)
- [Positive Label Is All You Need for Multi-Label Classification](https://mlsanity.com/paper/2306.16016/) (2023)
- [CoLLM-NAS: Collaborative Large Language Models for Efficient Knowledge-Guided Neural Architecture Search](https://mlsanity.com/paper/2509.26037/) (2025)
- [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)
- [Subnet-Aware Dynamic Supernet Training for Neural Architecture Search](https://mlsanity.com/paper/2503.10740/) (2025)
- [DCLP: Neural Architecture Predictor with Curriculum Contrastive Learning](https://mlsanity.com/paper/2302.13020/) (2023)
- [OSTA: One-shot Task-adaptive Channel Selection for Semantic Segmentation of Multichannel Images](https://mlsanity.com/paper/2305.04766/) (2023)
- [LISSNAS: Locality-based Iterative Search Space Shrinkage for Neural Architecture Search](https://mlsanity.com/paper/2307.03110/) (2023)
- [Farthest Greedy Path Sampling for Two-shot Recommender Search](https://mlsanity.com/paper/2310.20705/) (2023)

## Abstract (arXiv)

Training a good supernet in one-shot NAS methods is difficult since the search space is usually considerably huge (e.g., 1321). In order to enhance the supernet's evaluation ability, one greedy strategy is to sample good paths, and let the supernet lean towards the good ones and ease its evaluation burden as a result. However, in practice the search can be still quite inefficient since the identification of good paths is not accurate enough and sampled paths still scatter around the whole search space. In this paper, we leverage an explicit path filter to capture the characteristics of paths and directly filter those weak ones, so that the search can be thus implemented on the shrunk space more greedily and efficiently. Concretely, based on the fact that good paths are much less than the weak ones in the space, we argue that the label of "weak paths" will be more confident and reliable than that of "good paths" in multi-path sampling. In this way, we thus cast the training of path filter in the positive and unlabeled (PU) learning paradigm, and also encourage a textitpath embedding as better path/operation representation to enhance the identification capacity of the learned filter. By dint of this embedding, we can further shrink the search space by aggregating similar operations with similar embeddings, and the search can be more efficient and accurate. Extensive experiments validate the effectiveness of the proposed method GreedyNASv2. For example, our obtained GreedyNASv2-L achieves 81.1% Top-1 accuracy on ImageNet dataset, significantly outperforming the ResNet-50 strong baselines.