SOTAVerified

AutoML

Automated Machine Learning (AutoML) is a general concept which covers diverse techniques for automated model learning including automatic data preprocessing, architecture search, and model selection. Source: Evaluating recommender systems for AI-driven data science (1905.09205)

Source: CHOPT : Automated Hyperparameter Optimization Framework for Cloud-Based Machine Learning Platforms

Papers

Showing 5175 of 641 papers

TitleStatusHype
EA-HAS-Bench:Energy-Aware Hyperparameter and Architecture Search BenchmarkCode1
AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision TasksCode1
DriveML: An R Package for Driverless Machine LearningCode1
Efficient Hyper-parameter Search for Knowledge Graph EmbeddingCode1
AutoML Segmentation for 3D Medical Image Data: Contribution to the MSD Challenge 2018Code1
Direct Differentiable Augmentation SearchCode1
AnyMatch -- Efficient Zero-Shot Entity Matching with a Small Language ModelCode1
Architecture Disentanglement for Deep Neural NetworksCode1
AutoML Two-Sample TestCode1
Efficient Architecture Search for Diverse TasksCode1
DHP: Differentiable Meta Pruning via HyperNetworksCode1
Efficient AutoML Pipeline Search with Matrix and Tensor FactorizationCode1
Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?Code1
An Information Theory-inspired Strategy for Automatic Network PruningCode1
Deep-n-Cheap: An Automated Search Framework for Low Complexity Deep LearningCode1
AutoML for Climate Change: A Call to ActionCode1
Deep Fast Vision: Accelerated Deep Transfer Learning Vision Prototyping and BeyondCode1
Deep Pipeline Embeddings for AutoMLCode1
Conditional Positional Encodings for Vision TransformersCode1
Automating Outlier Detection via Meta-LearningCode1
AIPerf: Automated machine learning as an AI-HPC benchmarkCode1
Cross-Modal Fine-Tuning: Align then RefineCode1
DARTS-: Robustly Stepping out of Performance Collapse Without IndicatorsCode1
Automated Machine Learning Techniques for Data StreamsCode1
Automatically Optimized Gradient Boosting Trees for Classifying Large Volume High Cardinality Data Streams Under Concept DriftCode1
Show:102550
← PrevPage 3 of 26Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1marc.boulleRank (AutoML5)6.4Unverified
2reference_mbRank (AutoML5)5.2Unverified
3postech.mlg_exbrainRank (AutoML5)5.2Unverified
4abhishek4Rank (AutoML5)4.6Unverified
5referenceRank (AutoML5)4.4Unverified
6reference_lsRank (AutoML5)4Unverified
7djajeticRank (AutoML5)3Unverified
8aad_freiburgRank (AutoML5)1.6Unverified
#ModelMetricClaimedVerifiedStatus
1Logistic RegressionAccuracy97.02Unverified
#ModelMetricClaimedVerifiedStatus
1Zero-shot-BERT-SORT1:1 Accuracy55Unverified
#ModelMetricClaimedVerifiedStatus
1Logistic Regressionaccuracy98.33Unverified