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 751–800 of 1915 papers

TitleStatusHype
Architecture-Aware Minimization (A^2M): How to Find Flat Minima in Neural Architecture SearchCode0
Colab NAS: Obtaining lightweight task-specific convolutional neural networks following Occam's razorCode0
HYBRIDFORMER: improving SqueezeFormer with hybrid attention and NSR mechanismCode0
ImmuNetNAS: An Immune-network approach for searching Convolutional Neural Network ArchitecturesCode0
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image SegmentationCode0
3D-ANAS: 3D Asymmetric Neural Architecture Search for Fast Hyperspectral Image ClassificationCode0
Combinatorial Bayesian Optimization using the Graph Cartesian ProductCode0
Improving the Efficient Neural Architecture Search via Rewarding ModificationsCode0
Band-gap regression with architecture-optimized message-passing neural networksCode0
DVOLVER: Efficient Pareto-Optimal Neural Network Architecture SearchCode0
How to 0wn NAS in Your Spare TimeCode0
D-VAE: A Variational Autoencoder for Directed Acyclic GraphsCode0
How does topology of neural architectures impact gradient propagation and model performance?Code0
How to 0wn the NAS in Your Spare TimeCode0
DropNAS: Grouped Operation Dropout for Differentiable Architecture SearchCode0
BAM: Bottleneck Attention ModuleCode0
Homogeneous Architecture Augmentation for Neural PredictorCode0
HourNAS: Extremely Fast Neural Architecture Search Through an Hourglass LensCode0
Progressive DARTS: Bridging the Optimization Gap for NAS in the WildCode0
FlatNAS: optimizing Flatness in Neural Architecture Search for Out-of-Distribution RobustnessCode0
DPNAS: Neural Architecture Search for Deep Learning with Differential PrivacyCode0
Hierarchical Representations for Efficient Architecture SearchCode0
ABC-Di: Approximate Bayesian Computation for Discrete DataCode0
Do Not Train It: A Linear Neural Architecture Search of Graph Neural NetworksCode0
Adaptive hybrid activation function for deep neural networksCode0
HiveNAS: Neural Architecture Search using Artificial Bee Colony OptimizationCode0
Balanced Mixture of SuperNets for Learning the CNN Pooling ArchitectureCode0
Heterogeneous Graph Neural Architecture Search with GPT-4Code0
Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture SearchCode0
Improving the sample-efficiency of neural architecture search with reinforcement learningCode0
Guided Evolution for Neural Architecture SearchCode0
Backpropagation-Free 4D Continuous Ant-Based Neural Topology SearchCode0
GreenMachine: Automatic Design of Zero-Cost Proxies for Energy-Efficient NASCode0
B2EA: An Evolutionary Algorithm Assisted by Two Bayesian Optimization Modules for Neural Architecture SearchCode0
Distilled Pruning: Using Synthetic Data to Win the LotteryCode0
Autoequivariant Network Search via Group DecompositionCode0
Hardware Aware Neural Network Architectures using FbNetCode0
AdversarialNAS: Adversarial Neural Architecture Search for GANsCode0
From Xception to NEXcepTion: New Design Decisions and Neural Architecture SearchCode0
CONet: Channel Optimization for Convolutional Neural NetworksCode0
GraphNAS: Graph Neural Architecture Search with Reinforcement LearningCode0
A Variational-Sequential Graph Autoencoder for Neural Architecture Performance PredictionCode0
GRAN is superior to GraphRNN: node orderings, kernel- and graph embeddings-based metrics for graph generatorsCode0
FTT-NAS: Discovering Fault-Tolerant Convolutional Neural ArchitectureCode0
GraphPAS: Parallel Architecture Search for Graph Neural NetworksCode0
Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference CostCode0
DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image SegmentationCode0
A Classification of G-invariant Shallow Neural NetworksCode0
GradSign: Model Performance Inference with Theoretical InsightsCode0
Hardware/Software Co-Exploration of Neural ArchitecturesCode0
Show:102550
← PrevPage 16 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-SDARTS-RSAccuracy (Test)46.71—Unverified
4β-RDARTS-L2Accuracy (Test)46.71—Unverified
5NARAccuracy (Test)46.66—Unverified
6ASE-NAS+Accuracy (Val)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
7DARTS (first order)Top-1 Error Rate3—Unverified
8NN-MASS- CIFAR-ATop-1 Error Rate3—Unverified
9AlphaX-1 (cutout NASNet)Top-1 Error Rate2.82—Unverified
10NASGEPTop-1 Error Rate2.82—Unverified