# BlockQNN: Efficient Block-wise Neural Network Architecture Generation

arXiv: https://arxiv.org/abs/1808.05584 · HTML: https://mlsanity.com/paper/1808.05584/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Aug 2018.

## Built on by (most cited first, 30 of 31)

- [AutoBalance: Optimized Loss Functions for Imbalanced Data](https://mlsanity.com/paper/2201.01212/) (2022)
- [Neural Architecture Search with Random Labels](https://mlsanity.com/paper/2101.11834/) (2021)
- [Generalization Guarantees for Neural Architecture Search with Train-Validation Split](https://mlsanity.com/paper/2104.14132/) (2021)
- [Variational quantum compiling with double Q-learning](https://mlsanity.com/paper/2103.11611/) (2021)
- [A Survey on Computationally Efficient Neural Architecture Search](https://mlsanity.com/paper/2206.01520/) (2022)
- [Prior-Guided One-shot Neural Architecture Search](https://mlsanity.com/paper/2206.13329/) (2022)
- [IRLAS: Inverse Reinforcement Learning for Architecture Search](https://mlsanity.com/paper/1812.05285/) (2018)
- [Data-Free Neural Architecture Search via Recursive Label Calibration](https://mlsanity.com/paper/2112.02086/) (2021)
- [Quant 4.0: Engineering Quantitative Investment with Automated, Explainable and Knowledge-driven Artificial Intelligence](https://mlsanity.com/paper/2301.04020/) (2022)
- [Enhanced Gradient for Differentiable Architecture Search](https://mlsanity.com/paper/2103.12529/) (2021)
- [Collaboration of Experts: Achieving 80% Top-1 Accuracy on ImageNet with 100M FLOPs](https://mlsanity.com/paper/2107.03815/) (2021)
- [Observations on K-image Expansion of Image-Mixing Augmentation for Classification](https://mlsanity.com/paper/2110.04248/) (2021)
- [Discovering Physics-Informed Neural Networks Model for Solving Partial Differential Equations through Evolutionary Computation](https://mlsanity.com/paper/2405.11208/) (2024)
- [Accelerating Multi-Objective Neural Architecture Search by Random-Weight Evaluation](https://mlsanity.com/paper/2110.05242/) (2021)
- [When NAS Meets Trees: An Efficient Algorithm for Neural Architecture Search](https://mlsanity.com/paper/2204.04918/) (2022)
- [GeNAS: Neural Architecture Search with Better Generalization](https://mlsanity.com/paper/2305.08611/) (2023)
- [Vision Transformer with Convolutions Architecture Search](https://mlsanity.com/paper/2203.10435/) (2022)
- [Learning Low-Rank Representations for Model Compression](https://mlsanity.com/paper/2211.11397/) (2022)
- [Efficient Architecture Search via Bi-level Data Pruning](https://mlsanity.com/paper/2312.14200/) (2023)
- [Differentiable Neural Architecture Search with Morphism-based Transformable Backbone Architectures](https://mlsanity.com/paper/2106.07211/) (2021)
- [Multiple Population Alternate Evolution Neural Architecture Search](https://mlsanity.com/paper/2403.07035/) (2024)
- [Evolutionary Neural Architecture Search with Dual Contrastive Learning](https://mlsanity.com/paper/2512.20112/) (2025)
- [Designing the Architecture of a Convolutional Neural Network Automatically for Diabetic Retinopathy Diagnosis](https://mlsanity.com/paper/2110.03877/) (2021)
- [An Intelligent End-to-End Neural Architecture Search Framework for Electricity Forecasting Model Development](https://mlsanity.com/paper/2203.13563/) (2022)
- [NAS-based Recursive Stage Partial Network (RSPNet) for Light-Weight Semantic Segmentation](https://mlsanity.com/paper/2210.00698/) (2022)
- [FAQS: Communication-efficient Federate DNN Architecture and Quantization Co-Search for personalized Hardware-aware Preferences](https://mlsanity.com/paper/2210.08450/) (2022)
- [A Survey on Multi-Objective Neural Architecture Search](https://mlsanity.com/paper/2307.09099/) (2023)
- [Fair Differentiable Neural Network Architecture Search for Long-Tailed Data with Self-Supervised Learning](https://mlsanity.com/paper/2406.16949/) (2024)
- [A Survey on Neural Architecture Search Based on Reinforcement Learning](https://mlsanity.com/paper/2409.18163/) (2024)
- [Interpretable Recognition of Fused Magnesium Furnace Working Conditions with Deep Convolutional Stochastic Configuration Networks](https://mlsanity.com/paper/2501.02740/) (2025)

## Abstract (arXiv)

Convolutional neural networks have gained a remarkable success in computer vision. However, most usable network architectures are hand-crafted and usually require expertise and elaborate design. In this paper, we provide a block-wise network generation pipeline called BlockQNN which automatically builds high-performance networks using the Q-Learning paradigm with epsilon-greedy exploration strategy. The optimal network block is constructed by the learning agent which is trained to choose component layers sequentially. We stack the block to construct the whole auto-generated network. To accelerate the generation process, we also propose a distributed asynchronous framework and an early stop strategy. The block-wise generation brings unique advantages: (1) it yields state-of-the-art results in comparison to the hand-crafted networks on image classification, particularly, the best network generated by BlockQNN achieves 2.35% top-1 error rate on CIFAR-10. (2) it offers tremendous reduction of the search space in designing networks, spending only 3 days with 32 GPUs. A faster version can yield a comparable result with only 1 GPU in 20 hours. (3) it has strong generalizability in that the network built on CIFAR also performs well on the larger-scale dataset. The best network achieves very competitive accuracy of 82.0% top-1 and 96.0% top-5 on ImageNet.