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 801–850 of 1915 papers

TitleStatusHype
Neural Architecture Search for Energy Efficient Always-on Audio Models—0
B2EA: An Evolutionary Algorithm Assisted by Two Bayesian Optimization Modules for Neural Architecture SearchCode0
Heed the Noise in Performance Evaluations in Neural Architecture Search—0
NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy—0
AutoSNN: Towards Energy-Efficient Spiking Neural NetworksCode1
Generalized Global Ranking-Aware Neural Architecture Ranker for Efficient Image Classifier SearchCode1
AutoDistil: Few-shot Task-agnostic Neural Architecture Search for Distilling Large Language Models—0
Self Semi Supervised Neural Architecture Search for Semantic Segmentation—0
DropNAS: Grouped Operation Dropout for Differentiable Architecture SearchCode0
FRAMED: An AutoML Approach for Structural Performance Prediction of Bicycle Frames—0
PaRT: Parallel Learning Towards Robust and Transparent AICode0
Unifying and Boosting Gradient-Based Training-Free Neural Architecture SearchCode0
Neural Architecture Searching for Facial Attributes-based Depression Recognition—0
Neural Architecture Search for Spiking Neural NetworksCode1
NAS-VAD: Neural Architecture Search for Voice Activity DetectionCode1
AutoDistill: an End-to-End Framework to Explore and Distill Hardware-Efficient Language Models—0
A Deeper Look at Zero-Cost Proxies for Lightweight NAS—0
Landscape of Neural Architecture Search across sensors: how much do they differ ?—0
UDC: Unified DNAS for Compressible TinyML Models—0
Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019—0
Neural Architecture Search For LF-MMI Trained Time Delay Neural NetworksCode0
Neural Architecture Search for Inversion—0
Automated Graph Machine Learning: Approaches, Libraries, Benchmarks and DirectionsCode1
Searching the Deployable Convolution Neural Networks for GPUs—0
Neural Architecture Search With Representation Mutual InformationCode0
Performance-Aware Mutual Knowledge Distillation for Improving Neural Architecture Search—0
b-DARTS: Beta-Decay Regularization for Differentiable Architecture SearchCode1
Distribution Consistent Neural Architecture Search—0
Automatic Mixed-Precision Quantization Search of BERT—0
Designing the Topology of Graph Neural Networks: A Novel Feature Fusion PerspectiveCode1
SPIDER: Searching Personalized Neural Architecture for Federated Learning—0
Learn Layer-wise Connections in Graph Neural Networks—0
DARTS without a Validation Set: Optimizing the Marginal Likelihood—0
Enabling NAS with Automated Super-Network Generation—0
HyperSegNAS: Bridging One-Shot Neural Architecture Search with 3D Medical Image Segmentation using HyperNet—0
Automated Deep Learning: Neural Architecture Search Is Not the EndCode2
Learning Interpretable Models Through Multi-Objective Neural Architecture SearchCode0
M-FasterSeg: An Efficient Semantic Segmentation Network Based on Neural Architecture Search—0
Scale-Aware Neural Architecture Search for Multivariate Time Series ForecastingCode1
Auto-X3D: Ultra-Efficient Video Understanding via Finer-Grained Neural Architecture Search—0
GraphPAS: Parallel Architecture Search for Graph Neural NetworksCode0
Enhanced Exploration in Neural Feature Selection for Deep Click-Through Rate Prediction Models via Ensemble of Gating Layers—0
RSBNet: One-Shot Neural Architecture Search for A Backbone Network in Remote Sensing Image Recognition—0
Manas: Mining Software Repositories to Assist AutoMLCode0
Exploring Complicated Search Spaces with Interleaving-Free Sampling—0
Data-Free Neural Architecture Search via Recursive Label Calibration—0
The UniNAS framework: combining modules in arbitrarily complex configurations with argument trees—0
Learning from Mistakes based on Class Weighting with Application to Neural Architecture Search—0
Training BatchNorm Only in Neural Architecture Search and Beyond—0
Hardware-adaptive Efficient Latency Prediction for NAS via Meta-LearningCode1
Show:102550
← PrevPage 17 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