Neural Architecture Search

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

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 701–725 of 1915 papers

Title	Date	Tasks	Status	Hype
Search Space Adaptation for Differentiable Neural Architecture Search in Image Classification	Jun 5, 2022	image-classificationImage Classification	—Unverified	0
A Survey on Computationally Efficient Neural Architecture Search	Jun 3, 2022	Computational EfficiencyNeural Architecture Search	—Unverified	0
Supernet Training for Federated Image Classification under System Heterogeneity	Jun 3, 2022	ClassificationFederated Learning	CodeCode Available	0
Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization	Jun 2, 2022	Instance SegmentationNetwork Pruning	CodeCode Available	1
Multi-Complexity-Loss DNAS for Energy-Efficient and Memory-Constrained Deep Neural Networks	Jun 1, 2022	Neural Architecture Search	CodeCode Available	0
Automatic Relation-aware Graph Network Proliferation	May 31, 2022	Graph ClassificationGraph Learning	CodeCode Available	1
Uncertainty Quantification and Resource-Demanding Computer Vision Applications of Deep Learning	May 30, 2022	Neural Architecture SearchSurvey	—Unverified	0
Auto-PINN: Understanding and Optimizing Physics-Informed Neural Architecture	May 27, 2022	Hyperparameter OptimizationNeural Architecture Search	—Unverified	0
Concurrent Neural Tree and Data Preprocessing AutoML for Image Classification	May 25, 2022	AutoMLBIG-bench Machine Learning	—Unverified	0
MAPLE-X: Latency Prediction with Explicit Microprocessor Prior Knowledge	May 25, 2022	Neural Architecture SearchPrediction	—Unverified	0
FlexiBERT: Are Current Transformer Architectures too Homogeneous and Rigid?	May 23, 2022	Graph SimilarityNeural Architecture Search	—Unverified	0
A Hardware-Aware Framework for Accelerating Neural Architecture Search Across Modalities	May 19, 2022	Evolutionary Algorithmsimage-classification	—Unverified	0
AutoFAS: Automatic Feature and Architecture Selection for Pre-Ranking System	May 19, 2022	Information RetrievalNeural Architecture Search	—Unverified	0
Incremental Learning with Differentiable Architecture and Forgetting Search	May 19, 2022	Classificationimage-classification	—Unverified	0
A Classification of G-invariant Shallow Neural Networks	May 18, 2022	General ClassificationNeural Architecture Search	CodeCode Available	0
Heat Source Layout Optimization Using Automatic Deep Learning Surrogate and Multimodal Neighborhood Search Algorithm	May 16, 2022	Layout DesignManagement	—Unverified	0
Proxyless Neural Architecture Adaptation for Supervised Learning and Self-Supervised Learning	May 15, 2022	Neural Architecture SearchSelf-Supervised Learning	—Unverified	0
Warm-starting DARTS using meta-learning	May 12, 2022	AutoMLMeta-Learning	—Unverified	0
Deep Architecture Connectivity Matters for Its Convergence: A Fine-Grained Analysis	May 11, 2022	AutoMLNeural Architecture Search	CodeCode Available	0
AutoLC: Search Lightweight and Top-Performing Architecture for Remote Sensing Image Land-Cover Classification	May 11, 2022	DecoderLand Cover Classification	CodeCode Available	0
AutoKE: An automatic knowledge embedding framework for scientific machine learning	May 11, 2022	BIG-bench Machine LearningNeural Architecture Search	CodeCode Available	1
Efficient Automated Deep Learning for Time Series Forecasting	May 11, 2022	AutoMLBayesian Optimization	CodeCode Available	4
Neural Architecture Search using Property Guided Synthesis	May 8, 2022	Neural Architecture Search	—Unverified	0
A Collaboration Strategy in the Mining Pool for Proof-of-Neural-Architecture Consensus	May 5, 2022	Deep LearningNeural Architecture Search	—Unverified	0
Gait Recognition in the Wild: A Large-scale Benchmark and NAS-based Baseline	May 5, 2022	Gait RecognitionGait Recognition in the Wild	CodeCode Available	0

Show:10 25 50

← PrevPage 29 of 77Next →

All datasets ImageNet NAS-Bench-201, ImageNet-16-120 CIFAR-10 NAS-Bench-201, CIFAR-100 NAS-Bench-201, CIFAR-10 CIFAR-10 Image Classification CIFAR-100 NATS-Bench Topology, CIFAR-10 NATS-Bench Topology, CIFAR-100 NATS-Bench Topology, ImageNet16-120 Food-101 NAS-Bench-101

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	SPOS (ProxylessNAS (GPU) latency)	Accuracy	75.3	—	Unverified
2	SPOS (FBNet-C latency)	Accuracy	75.1	—	Unverified
3	SPOS (block search + channel search)	Accuracy	74.7	—	Unverified
4	MUXNet-xs	Top-1 Error Rate	33.3	—	Unverified
5	FBNetV2-F1	Top-1 Error Rate	31.7	—	Unverified
6	LayerNAS-60M	Top-1 Error Rate	31	—	Unverified
7	NASGEP	Top-1 Error Rate	29.51	—	Unverified
8	MUXNet-s	Top-1 Error Rate	28.4	—	Unverified
9	NN-MASS-A	Top-1 Error Rate	27.1	—	Unverified
10	FBNetV2-F3	Top-1 Error Rate	26.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CR-LSO	Accuracy (Test)	46.98	—	Unverified
2	Shapley-NAS	Accuracy (Test)	46.85	—	Unverified
3	β-RDARTS-L2	Accuracy (Test)	46.71	—	Unverified
4	β-SDARTS-RS	Accuracy (Test)	46.71	—	Unverified
5	ASE-NAS+	Accuracy (Val)	46.66	—	Unverified
6	NAR	Accuracy (Test)	46.66	—	Unverified
7	BaLeNAS-TF	Accuracy (Test)	46.54	—	Unverified
8	AG-Net	Accuracy (Test)	46.42	—	Unverified
9	Local search	Accuracy (Test)	46.38	—	Unverified
10	NASBOT	Accuracy (Test)	46.37	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Balanced Mixture	Accuracy (% )	91.55	—	Unverified
2	GDAS	Top-1 Error Rate	3.4	—	Unverified
3	Bonsai-Net	Top-1 Error Rate	3.35	—	Unverified
4	Net2 (2)	Top-1 Error Rate	3.3	—	Unverified
5	μDARTS	Top-1 Error Rate	3.28	—	Unverified
6	NN-MASS- CIFAR-C	Top-1 Error Rate	3.18	—	Unverified
7	NN-MASS- CIFAR-A	Top-1 Error Rate	3	—	Unverified
8	DARTS (first order)	Top-1 Error Rate	3	—	Unverified
9	NASGEP	Top-1 Error Rate	2.82	—	Unverified
10	AlphaX-1 (cutout NASNet)	Top-1 Error Rate	2.82	—	Unverified