SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 201–250 of 1915 papers

TitleStatusHype
Efficient Architecture Search for Diverse TasksCode1
Integrating Large Circular Kernels into CNNs through Neural Architecture SearchCode1
AutoSTR: Efficient Backbone Search for Scene Text RecognitionCode1
ISTA-NAS: Efficient and Consistent Neural Architecture Search by Sparse CodingCode1
EH-DNAS: End-to-End Hardware-aware Differentiable Neural Architecture SearchCode1
AutoInit: Analytic Signal-Preserving Weight Initialization for Neural NetworksCode1
AutoKE: An automatic knowledge embedding framework for scientific machine learningCode1
Accelerating Neural Architecture Search via Proxy DataCode1
DARTS-: Robustly Stepping out of Performance Collapse Without IndicatorsCode1
DC-BENCH: Dataset Condensation BenchmarkCode1
Automated Concatenation of Embeddings for Structured PredictionCode1
AutoSpeech: Neural Architecture Search for Speaker RecognitionCode1
DataDAM: Efficient Dataset Distillation with Attention MatchingCode1
Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and DirectionsCode1
AdvRush: Searching for Adversarially Robust Neural ArchitecturesCode1
Automated Machine Learning on Graphs: A SurveyCode1
Dataset Condensation with Distribution MatchingCode1
Differentiable Neural Architecture Search for Extremely Lightweight Image Super-ResolutionCode1
Automated Model Design and Benchmarking of 3D Deep Learning Models for COVID-19 Detection with Chest CT ScansCode1
An Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter OptimizationCode1
Automated Search for Resource-Efficient Branched Multi-Task NetworksCode1
Local Search is a Remarkably Strong Baseline for Neural Architecture SearchCode1
DU-DARTS: Decreasing the Uncertainty of Differentiable Architecture SearchCode1
Meta-prediction Model for Distillation-Aware NAS on Unseen DatasetsCode1
Automatic Relation-aware Graph Network ProliferationCode1
MiLeNAS: Efficient Neural Architecture Search via Mixed-Level ReformulationCode1
DrNAS: Dirichlet Neural Architecture SearchCode1
MnasNet: Platform-Aware Neural Architecture Search for MobileCode1
AOWS: Adaptive and optimal network width search with latency constraintsCode1
DSNAS: Direct Neural Architecture Search without Parameter RetrainingCode1
Deep Multimodal Neural Architecture SearchCode1
AutoML: A Survey of the State-of-the-ArtCode1
deepstruct -- linking deep learning and graph theoryCode1
MPCViT: Searching for Accurate and Efficient MPC-Friendly Vision Transformer with Heterogeneous AttentionCode1
DEHB: Evolutionary Hyperband for Scalable, Robust and Efficient Hyperparameter OptimizationCode1
AutoMoE: Heterogeneous Mixture-of-Experts with Adaptive Computation for Efficient Neural Machine TranslationCode1
EAGAN: Efficient Two-stage Evolutionary Architecture Search for GANsCode1
Multi-Objective Evolutionary Design of Deep Convolutional Neural Networks for Image ClassificationCode1
Designing the Topology of Graph Neural Networks: A Novel Feature Fusion PerspectiveCode1
MUXConv: Information Multiplexing in Convolutional Neural NetworksCode1
AutoPEFT: Automatic Configuration Search for Parameter-Efficient Fine-TuningCode1
Angle-based Search Space Shrinking for Neural Architecture SearchCode1
DHP: Differentiable Meta Pruning via HyperNetworksCode1
Differentiable Model Scaling using Differentiable TopkCode1
Discretization-Aware Architecture SearchCode1
NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse TasksCode1
Differentiable Neural Architecture Learning for Efficient Neural Network DesignCode1
AutoReCon: Neural Architecture Search-based Reconstruction for Data-free CompressionCode1
NAS-BNN: Neural Architecture Search for Binary Neural NetworksCode1
AutoSNN: Towards Energy-Efficient Spiking Neural NetworksCode1
Show:102550
← PrevPage 5 of 39Next →
All datasetsImageNetNAS-Bench-201, ImageNet-16-120CIFAR-10NAS-Bench-201, CIFAR-100NAS-Bench-201, CIFAR-10CIFAR-10 Image ClassificationCIFAR-100NATS-Bench Topology, CIFAR-10NATS-Bench Topology, CIFAR-100NATS-Bench Topology, ImageNet16-120Food-101NAS-Bench-101

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SPOS (ProxylessNAS (GPU) latency)Accuracy75.3—Unverified
2SPOS (FBNet-C latency)Accuracy75.1—Unverified
3SPOS (block search + channel search)Accuracy74.7—Unverified
4MUXNet-xsTop-1 Error Rate33.3—Unverified
5FBNetV2-F1Top-1 Error Rate31.7—Unverified
6LayerNAS-60MTop-1 Error Rate31—Unverified
7NASGEPTop-1 Error Rate29.51—Unverified
8MUXNet-sTop-1 Error Rate28.4—Unverified
9NN-MASS-ATop-1 Error Rate27.1—Unverified
10FBNetV2-F3Top-1 Error Rate26.8—Unverified
#ModelMetricClaimedVerifiedStatus
1CR-LSOAccuracy (Test)46.98—Unverified
2Shapley-NASAccuracy (Test)46.85—Unverified
3β-RDARTS-L2Accuracy (Test)46.71—Unverified
4β-SDARTS-RSAccuracy (Test)46.71—Unverified
5ASE-NAS+Accuracy (Val)46.66—Unverified
6NARAccuracy (Test)46.66—Unverified
7BaLeNAS-TFAccuracy (Test)46.54—Unverified
8AG-NetAccuracy (Test)46.42—Unverified
9Local searchAccuracy (Test)46.38—Unverified
10NASBOTAccuracy (Test)46.37—Unverified
#ModelMetricClaimedVerifiedStatus
1Balanced MixtureAccuracy (% )91.55—Unverified
2GDASTop-1 Error Rate3.4—Unverified
3Bonsai-NetTop-1 Error Rate3.35—Unverified
4Net2 (2)Top-1 Error Rate3.3—Unverified
5μDARTSTop-1 Error Rate3.28—Unverified
6NN-MASS- CIFAR-CTop-1 Error Rate3.18—Unverified
7NN-MASS- CIFAR-ATop-1 Error Rate3—Unverified
8DARTS (first order)Top-1 Error Rate3—Unverified
9NASGEPTop-1 Error Rate2.82—Unverified
10AlphaX-1 (cutout NASNet)Top-1 Error Rate2.82—Unverified