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 76100 of 641 papers

TitleStatusHype
Efficient Hyper-parameter Search for Knowledge Graph EmbeddingCode1
Efficient Relation-aware Scoring Function Search for Knowledge Graph EmbeddingCode1
AutoML Two-Sample TestCode1
AutoDC: Automated data-centric processingCode1
Efficient AutoML Pipeline Search with Matrix and Tensor FactorizationCode1
AutoML Segmentation for 3D Medical Image Data: Contribution to the MSD Challenge 2018Code1
Embedding in Recommender Systems: A SurveyCode1
AutoMMLab: Automatically Generating Deployable Models from Language Instructions for Computer Vision TasksCode1
Efficient End-to-End AutoML via Scalable Search Space DecompositionCode1
Fast Optimizer BenchmarkCode1
AutoML for Climate Change: A Call to ActionCode1
Conditional Positional Encodings for Vision TransformersCode1
AutoField: Automating Feature Selection in Deep Recommender SystemsCode1
DriveML: An R Package for Driverless Machine LearningCode1
AutoSmart: An Efficient and Automatic Machine Learning framework for Temporal Relational DataCode1
AutoGAN-Distiller: Searching to Compress Generative Adversarial NetworksCode1
AutoGL: A Library for Automated Graph LearningCode1
AutoML: A Survey of the State-of-the-ArtCode1
Does Unsupervised Architecture Representation Learning Help Neural Architecture Search?Code1
EA-HAS-Bench:Energy-Aware Hyperparameter and Architecture Search BenchmarkCode1
Deep Pipeline Embeddings for AutoMLCode1
Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter OptimizationCode1
Deep-n-Cheap: An Automated Search Framework for Low Complexity Deep LearningCode1
DHP: Differentiable Meta Pruning via HyperNetworksCode1
Automatically Optimized Gradient Boosting Trees for Classifying Large Volume High Cardinality Data Streams Under Concept DriftCode1
Show:102550
← PrevPage 4 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