Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

methodology-6

Neural Architecture Search

3260 papers • 126 benchmarks • 313 datasets

Neural architecture search (NAS) is a technique for automating the design of artificial neural networks (ANN), a widely used model in the field of machine learning. NAS essentially takes the process of a human manually tweaking a neural network and learning what works well, and automates this task to discover more complex architectures. Image Credit : NAS with Reinforcement Learning

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in neural-architecture-search-12

Trend

Dataset

Best Model

Actions

ImageNet

ImageNet

NAS-Bench-201, ImageNet-16-120

NAS-Bench-201, ImageNet-16-120

CIFAR-10

Libraries

i

Use these libraries to find neural-architecture-search-12 models and implementations

10 papers 2,915

Datasets

CIFAR-10

ImageNet

CIFAR-100

MNIST

Oxford 102 Flower

Oxford 102 Flower

Subtasks

Activation Function Synthesis

Most implemented papers

Proximal Policy Optimization Algorithms

Alec Radford, Filip Wolski, John Schulman, Oleg Klimov, Prafulla Dhariwal•Wed Jul 19 2017

A new family of policy gradient methods for reinforcement learning, which alternate between sampling data through interaction with the environment, and optimizing a "surrogate" objective function using stochastic gradient ascent, are proposed.

24784

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

CIFAR-10

NAS-Bench-201, CIFAR-100

NAS-Bench-201, CIFAR-100

NAS-Bench-201, CIFAR-10

NAS-Bench-201, CIFAR-10

CIFAR-10 Image Classification

CIFAR-10 Image Classification

CIFAR-100

CIFAR-100

NATS-Bench Topology, ImageNet16-120

NATS-Bench Topology, ImageNet16-120

NATS-Bench Topology, CIFAR-10

NATS-Bench Topology, CIFAR-10

NATS-Bench Topology, CIFAR-100

NATS-Bench Topology, CIFAR-100

NAS-Bench-101

NAS-Bench-101

Oxford 102 Flowers

Oxford 102 Flowers

Oxford-IIIT Pet Dataset

Oxford-IIIT Pet Dataset

DTD

DTD

STL-10

STL-10

FGVC Aircraft

FGVC Aircraft

Stanford Cars

Stanford Cars

Food-101

Food-101

CINIC-10

CINIC-10

NATS-Bench Size, CIFAR-10

NATS-Bench Size, CIFAR-10

NATS-Bench Size, CIFAR-100

NATS-Bench Size, CIFAR-100

NAS-Bench-201

NAS-Bench-201

MNIST

MNIST

LIDC-IDRI

LIDC-IDRI

NATS-Bench Size, ImageNet16-120

NATS-Bench Size, ImageNet16-120

NAS-Bench-301

NAS-Bench-301

rwightman/pytorch-image-models

7 papers 29,556

D-X-Y/NAS-Projects

6 papers 1,546

D-X-Y/AutoDL-Projects

6 papers 1,546

DataCanvasIO/Hypernets

6 papers 259

5 papers 1,546

facebookresearch/LaMCTS

5 papers 443

5 papers 216

cogsys-tuebingen/uninas

5 papers 22

4 papers 15,348

Deci-AI/super-gradients

4 papers 4,303

mit-han-lab/once-for-all

4 papers 1,834

open-mmlab/mmrazor

4 papers 1,351

jim-schwoebel/allie

4 papers 138

open-mmlab/mmdetection

3 papers 27,612

microsoft/cream

3 papers 1,547

gouthamvgk/coreml_conversion_hub

3 papers 36

NVIDIA/DeepLearningExamples

2 papers 12,558

PaddlePaddle/PaddleDetection

2 papers 11,993

awslabs/autogluon

2 papers 7,042

autogluon/autogluon

2 papers 7,042

open-mmlab/mmpose

2 papers 4,932

tianyic/only_train_once

2 papers 259

2 papers 26

STL-10

STL-10

Stanford Cars

DTD

Food-101

FGVC-Aircraft

0

EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks

Quoc V. Le, Mingxing Tan•Thu May 23 2019

A new scaling method is proposed that uniformly scales all dimensions of depth/width/resolution using a simple yet highly effective compound coefficient and is demonstrated the effectiveness of this method on scaling up MobileNets and ResNet.

22147 0

Searching for MobileNetV3

Quoc V. Le, Liang-Chieh Chen, Andrew G. Howard, Vijay Vasudevan, Mingxing Tan, Ruoming Pang, Hartwig Adam, Grace Chu, Weijun Wang, Yukun Zhu, M. Sandler, Bo Chen•Sun May 05 2019

This paper starts the exploration of how automated search algorithms and network design can work together to harness complementary approaches improving the overall state of the art of MobileNets.

8598 0

DARTS: Differentiable Architecture Search

K. Simonyan, Yiming Yang, Hanxiao Liu•Sat Jun 23 2018

The proposed algorithm excels in discovering high-performance convolutional architectures for image classification and recurrent architectures for language modeling, while being orders of magnitude faster than state-of-the-art non-differentiable techniques.

4777 0

Efficient Neural Architecture Search via Parameter Sharing

J. Dean, Quoc V. Le, Barret Zoph, Hieu Pham, M. Guan•Thu Feb 08 2018

Efficient Neural Architecture Search is a fast and inexpensive approach for automatic model design that establishes a new state-of-the-art among all methods without post-training processing and delivers strong empirical performances using much fewer GPU-hours.

2937 0

MnasNet: Platform-Aware Neural Architecture Search for Mobile

Quoc V. Le, Vijay Vasudevan, Mingxing Tan, Ruoming Pang•Mon Jul 30 2018

An automated mobile neural architecture search (MNAS) approach, which explicitly incorporate model latency into the main objective so that the search can identify a model that achieves a good trade-off between accuracy and latency.

3312 0

ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

Song Han, Ligeng Zhu, Han Cai•Wed Sep 26 2018

ProxylessNAS is presented, which can directly learn the architectures for large-scale target tasks and target hardware platforms and apply ProxylessNAS to specialize neural architectures for hardware with direct hardware metrics (e.g. latency) and provide insights for efficient CNN architecture design.

2005 0

EfficientNetV2: Smaller Models and Faster Training

Mingxing Tan, Quoc V. Le•Wed Mar 31 2021

This paper introduces EfficientNetV2, a new family of convolutional networks that have faster training speed and better parameter efficiency than previous models that were searched from the search space enriched with new ops such as Fused-MBConv.

3840 0

Learning Transferable Architectures for Scalable Image Recognition

Jonathon Shlens, Vijay Vasudevan, Barret Zoph, Quoc V. Le•Thu Jul 20 2017

This paper proposes to search for an architectural building block on a small dataset and then transfer the block to a larger dataset and introduces a new regularization technique called ScheduledDropPath that significantly improves generalization in the NASNet models.

5970 0

Progressive Neural Architecture Search

K. Murphy, Li-Jia Li, Li Fei-Fei, A. Yuille, Jonathon Shlens, Chenxi Liu, Barret Zoph, Jonathan Huang, Wei Hua•Fri Dec 01 2017

This work proposes a new method for learning the structure of convolutional neural networks (CNNs) that is more efficient than recent state-of-the-art methods based on reinforcement learning and evolutionary algorithms using a sequential model-based optimization (SMBO) strategy.

2105 0

Adding a benchmark result helps the community track progress.

Neural Architecture Search | State-of-the-Art