awesome-automl

collecting related resources of automated machine learning here
https://github.com/ChanChiChoi/awesome-automl

Last synced: 3 days ago
JSON representation

Uncategorized
- Uncategorized
  - x
  - x
  - x
Papers
- Metalearning - A Tutorial
- Neuroevolution:from architectures to learning
- Feature selection as a one-player game - -366.
- Auto-WEKA: Combined selection and hyperparameter optimization of classification algorithms - 855.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Bayesian optimization with robust bayesian neural networks - 4142.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Learning transferable architectures for scalable image recognition
- Practical network blocks design with q-learning
- Neural optimizer search with reinforcement learning
- Feature Engineering for Predictive Modeling using Reinforcement Learning
- Learning to Warm-Start Bayesian Hyperparameter Optimization
- Hierarchical representations for efficient architecture search
- Simple and efficient architecture search for convolutional neural networks
- Population Based Training of Neural Networks
- Progressive neural architecture search
- Finding Competitive Network Architectures Within a Day Using UCT
- ATM: A distributed, collaborative, scalable system for automated machine learning
- SMASH: one-shot model architecture search through hypernetworks
- Google vizier: A service for black-box optimization - 1495.
- Learning feature engineering for classification - 2535.
- Automatic Frankensteining: Creating Complex Ensembles Autonomously
- Regularized Evolution for Image Classifier Architecture Search
- Efficient Neural Architecture Search via Parameter Sharing
- Neural Architecture Search with Bayesian Optimisation and Optimal Transport
- Stochastic Hyperparameter Optimization through Hypernetworks
- Autopythonstacker: A Compositional Evolutionary Learning System
- Transfer Automatic Machine Learning
- Neural Architecture Construction using EnvelopeNets
- MLtuner: System Support for Automatic Machine Learning Tuning
- GitGraph-from Computational Subgraphs to Smaller Architecture Search Spaces
- PPP-Net: Platform-aware Progressive Search for Pareto-optimal Neural Architectures
- Accelerating Neural Architecture Search using Performance Prediction
- GNAS: A Greedy Neural Architecture Search Method for Multi-Attribute Learning.
- The cascade correlation learning architecture
- Evolving neural networks through augmenting topologies - 127.
- Metalearning - A Tutorial
- Neuroevolution:from architectures to learning
- ParamILS: an automatic algorithm configuration framework - 306.
- A hypercube-based encoding for evolving large-scale neural networks
- A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
- Feature selection as a one-player game - -366.
- Sequential model-based optimization for general algorithm configuration - 523.
- Collaborative hyperparameter tuning - 207.
- Efficient Architecture Search by Network Transformation
- Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures
- Hyperparameter Optimization and Boosting for Classifying Facial Expressions: How good can a "Null" Model be?
- Gradient-based Hyperparameter Optimization through Reversible Learning
- Non-stochastic Best Arm Identification and Hyperparameter Optimization
- Optimizing deep learning hyper-parameters through an evolutionary algorithm - Performance Computing Environments. ACM, 2015: 4.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- AutoCompete: A Framework for Machine Learning Competition
- Deep feature synthesis: Towards automating data science endeavors - 10.
- Towards automatically-tuned neural networks - 65.
- Hyperparameter optimization with approximate gradient
- Hyperband: A novel bandit-based approach to hyperparameter optimization
- CMA-ES for hyperparameter optimization of deep neural networks
- Bayesian Hyperparameter Optimization for Ensemble Learning
- Fast bayesian optimization of machine learning hyperparameters on large datasets
- Learning to optimize
- Convolutional neural fabrics - 4061.
- Adanet: Adaptive structural learning of artificial neural networks
- Efficient Hyperparameter Optimization of Deep Learning Algorithms Using Deterministic RBF Surrogates
- Hyperparameter Transfer Learning through Surrogate Alignment for Efficient Deep Neural Network Training
- Neural architecture search with reinforcement learning
- Designing neural network architectures using reinforcement learning
- Learning curve prediction with Bayesian neural networks
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Towards automatically-tuned neural networks - 65.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Evolving deep neural networks
- Large-scale evolution of image classifiers
- Genetic cnn
- Forward and Reverse Gradient-Based Hyperparameter Optimization
- Global optimization of Lipschitz functions
- A genetic programming approach to designing convolutional neural network architectures
- Deeparchitect: Automatically designing and training deep architectures
- An effective algorithm for hyperparameter optimization of neural networks
- One button machine for automating feature engineering in relational databases
- Hyperparameter Optimization: A Spectral Approach
- Open Loop Hyperparameter Optimization and Determinantal Point Processes Machine Learning
- Learning deep resnet blocks sequentially using boosting theory
- autoBagging: Learning to Rank Bagging Workflows with Metalearning
- ParamILS: an automatic algorithm configuration framework - 306.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Learning to optimize
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Global optimization of Lipschitz functions
- Feature Engineering for Predictive Modeling using Reinforcement Learning
- Autopythonstacker: A Compositional Evolutionary Learning System
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Neuroevolution:from architectures to learning
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Neuroevolution:from architectures to learning
- Neuroevolution:from architectures to learning
- Optimizing deep learning hyper-parameters through an evolutionary algorithm - Performance Computing Environments. ACM, 2015: 4.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Neuroevolution:from architectures to learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Neuroevolution:from architectures to learning
- A Tutorial on Bayesian Optimization of Expensive Cost Functions, with Application to Active User Modeling and Hierarchical Reinforcement Learning
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- AutoCompete: A Framework for Machine Learning Competition
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Cross-disciplinary perspectives on meta-learning for algorithm selection
- A hypercube-based encoding for evolving large-scale neural networks
- Algorithms for hyper-parameter optimization - 2554.
- Random search for hyper-parameter optimization - 305.
- Collaborative hyperparameter tuning - 207.
- Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures
- Sequential model-free hyperparameter tuning - 1038.
- Scalable bayesian optimization using deep neural networks - 2180.
- Learning hyperparameter optimization initializations - 10.
- Joint model choice and hyperparameter optimization with factorized multilayer perceptrons - 79.
- Hyperparameter search space pruning–a new component for sequential model-based hyperparameter optimization - 119.
- Hyperparameter optimization with factorized multilayer perceptrons - 103.
- Efficient and robust automated machine learning - 2970.
- Towards automatically-tuned neural networks - 65.
- Fast bayesian optimization of machine learning hyperparameters on large datasets
- Hyperparameter optimization machines - 50.
- Flexible transfer learning framework for bayesian optimisation - Asia Conference on Knowledge Discovery and Data Mining. Springer, Cham, 2016: 102-114.
- Two-stage transfer surrogate model for automatic hyperparameter optimization - 214.
- Taking the human out of the loop: A review of bayesian optimization - 175.
- Scalable hyperparameter optimization with products of gaussian process experts - 48.
- Cognito: Automated feature engineering for supervised learning - 1307.
- Explorekit: Automatic feature generation and selection - 984.
- One button machine for automating feature engineering in relational databases
- Particle swarm optimization for hyper-parameter selection in deep neural networks - 488.
SURVEY
blogs & articles & book
Libraries
- - HDI-Project/AutobBzaar
  - HDI-Project/BTB - tuning systems such as AutoML systems. It provides an easy-to-use interface for tuning and selection
  - CiscoAI/amla
  - dataloop-ai/zazuml - source AutoML framework for object detection. Currently this project contains a model & hyper-parameter tuner, auto augmentations, trial manager and prediction trigger, already loaded with your top preforming model-checkpoint. A working pipeline ready to be plugged into your product, simple as that
  - SoftwareAG/mlw - learning platforms to support the Predictive Model Markup Languaue (PMML) format, PMML allows for different statistical and data mining tools to speak the same language.
  - thomas-young-2013/alpha-ml - ML is a high-level AutoML toolkit, written in Python
  - SaltWaterStudio/modgen
  - onepanelio/automl - processing, feature selection, and feature engineering methods along with machine learning methods and parameter settings that are optimized for your data
  - yeticloud/dama
  - MateLabs
  - paper
  - paper
  - paper
  - paper
  - facebook/AX - purpose platform for understanding, managing, deploying, and automating adaptive experiments. Adaptive experimentation is the machine-learning guided process of iteratively exploring a (possibly infinite) parameter space in order to identify optimal configurations in a resource-efficient manner. Ax currently supports Bayesian optimization and bandit optimization as exploration strategies. Bayesian optimization in Ax is powered by BoTorch, a modern library for Bayesian optimization research built on PyTorch
  - google-research/automl_zero - Zero aims to automatically discover computer programs that can solve machine learning tasks, starting from empty or random programs and using only basic math operations. The goal is to simultaneously search for all aspects of an ML algorithm—including the model structure and the learning strategy—while employing minimal human bias.
  - SigOpt - grade optimization platform and API designed to unlock the potential of your modeling pipelines. This fully agnostic software solution accelerates, amplifies, and scales the model development process.
  - S - supervised): An Automated Machine Learning (AutoML) python package for tabular data. It can handle: Binary Classification, MultiClass Classification and Regression. It provides explanations and markdown reports.
  - AutoCross
  - DarwinML
  - MateLabs
  - DataRobot - star lineup of expert speakers how to best leverage AI today to build business resilience, reduce costs, and speed time to results
  - mlpapers/automl
  - shukwong/awesome_automl_libraries
  - Rakib091998/Auto_ML
  - DeepHiveMind/AutoML_AutoKeras_HPO
  - theainerd/automated-machine-learning
  - SIAN - accuracy deep learning models on tabular, image, and text data
  - awslabs/adatune - HD, RTHO and our newly proposed algorithm, MARTHE. The repository also contains other commonly used non-adaptive learning_rate adaptation strategies like staircase-decay, exponential-decay and cosine-annealing-with-restarts. The library is implemented in PyTorch
  - pycaret/pycaret - code machine learning library in Python that aims to reduce the hypothesis to insights cycle time in a ML experiment. It enables data scientists to perform end-to-end experiments quickly and efficiently. In comparison with the other open source machine learning libraries, PyCaret is an alternative low-code library that can be used to perform complex machine learning tasks with only few lines of code. PyCaret is essentially a Python wrapper around several machine learning libraries and frameworks such as scikit-learn, XGBoost, Microsoft LightGBM, spaCy and many more.
  - IN - parameter tuning
  - SIAN
  - FeatureLabs/Featuretools
  - automl/auto-sklearn - in replacement for scikit-learn estimators.
  - automl/Auto-Pytorch
  - automl/RoBO
  - automl/Auto-WEKA - WEKA, wich provides automatic selection of models and hyperparameters for WEKA
  - automl/SMAC3
  - NVIDIA/Milano
  - kubeflow/katib - based system for Hyperparameter Tuning and Neural Architecture Search. Katib supports a number of ML frameworks, including TensorFlow, Apache MXNet, PyTorch, XGBoost, and others
  - I
  - keras-team/keras-tuner
  - HDI-Project/AutobBzaar
  - tensorflow/adanet - based framework for automatically learning high-quality models with minimal expert intervention. AdaNet builds on recent AutoML efforts to be fast and flexible while providing learning guarantees. Importantly, AdaNet provides a general framework for not only learning a neural network architecture, but also for learning to ensemble to obtain even better models
  - IBM/lale - automated data science. Lale makes it easy to automatically select algorithms and tune hyperparameters of pipelines that are compatible with scikit-learn, in a type-safe fashion. If you are a data scientist who wants to experiment with automated machine learning, this library is for you! Lale adds value beyond scikit-learn along three dimensions: automation, correctness checks, and interoperability. For automation, Lale provides a consistent high-level interface to existing pipeline search tools including Hyperopt, GridSearchCV, and SMAC. For correctness checks, Lale uses JSON Schema to catch mistakes when there is a mismatch between hyperparameters and their type, or between data and operators. And for interoperability, Lale has a growing library of transformers and estimators from popular libraries such as scikit-learn, XGBoost, PyTorch etc. Lale can be installed just like any other Python package and can be edited with off-the-shelf Python tools such as Jupyter notebooks
  - ARM-software/mango
  - mindsdb/mindsdb
  - EpistasisLab/TPOT - learn
  - Neuraxio/Neuraxle - like Framework for Hyperparameter Tuning and AutoML in Deep Learning projects. Finally have the right abstractions and design patterns to properly do AutoML. Let your pipeline steps have hyperparameter spaces. Enable checkpoints to cut duplicate calculations. Go from research to production environment easily.
  - deephyper/deephyper - performing the deep neural network search_space. 2) Hyperparameter search is an approach for automatically searching for high-performing hyperparameters for a given deep neural network. DeepHyper provides an infrastructure that targets experimental research in neural architecture and hyperparameter search methods, scalability, and portability across HPC systems. It comprises three modules: benchmarks, a collection of extensible and diverse benchmark problems; search, a set of search algorithms for neural architecture search and hyperparameter search; and evaluators, a common interface for evaluating hyperparameter configurations on HPC platforms
  - Ashton-Sidhu/aethos - kit learn, gensim, etc
  - hyperopt/Hyperopt-sklearn - sklearn is Hyperopt-based model selection among machine learning algorithms in scikit-learn.
  - autogoal/autogoal
  - optuna/optuna - by-run style user API. Thanks to our define-by-run API, the code written with Optuna enjoys high modularity, and the user of Optuna can dynamically construct the search spaces for the hyperparameters
  - DataCanvasIO/Hypernets
  - LGE-ARC-AdvancedAI/Auptimizer - Start using Auptimizer by changing just a few lines of your code. It will run and record sophisticated hyperparameter optimization (HPO) experiments for you, resulting in effortless consistency and reproducibility.2)
  - fmfn/BayesianOptimization
  - rmcantin/BayesOpt
  - Angle-ml/automl - AutoML provides automatic hyper-parameter tuning and feature engineering operators. It is developed with Scala. As a stand-alone library, Angel-AutoML can be easily integrated in Java and Scala projects.
  - auto-flow/auto-flow
  - scikit-optimize/Scikit-Optimize - Optimize, or skopt, is a simple and efficient library to minimize (very) expensive and noisy black-box functions. It implements several methods for sequential model-based optimization. skopt aims to be accessible and easy to use in many contexts
  - cod3licious/autofeat
  - S - of-the art Automated Machine Learning python library for Tabular Data
  - joeddav/DEvol
  - AutoViML/auto_ts - ts is an Automated ML library for time series data. auto-ts enables you to build and select multiple time series models using techniques such as ARIMA, SARIMAX, VAR, decomposable (trend+seasonality+holidays) models, and ensemble machine learning models.
  - gfluz94/aautoml-gfluz - learn and pycaret, in order to provide a pipeline which suits every supervised problem. Therefore, data scientists can spend less time working on building pipelines and use this time more wisely to create new features and tune the best model.
  - societe-generale/aikit
  - souryadey/deep-n-cheap - n-Cheap – an AutoML framework to search for deep learning models
  - deil87/automl-genetic
  - CleverInsight/cognito - learning format. We at CleverInsight Open Ai Foundation took the initiative to build a better automated data preprocessing library and here it is
  - kxsystems/automl - world problems. In the absence of expert machine learning engineers this handles the following processes within a traditional workflow
  - Media-Smart/volkstuner
  - mihaianton/automl - Of-The-Art data engineering techniques towards building an off the box machine learning solution
  - epeters3/skplumber - Learn.Making the best use of your compute-resources - Whether you are using a couple of GPUs or AWS, Auptimizer will help you orchestrate compute resources for faster hyperparameter tuning.3)Getting the best models in minimum time - Generate optimal models and achieve better performance by employing state-of-the-art HPO techniques. Auptimizer provides a single seamless access point to top-notch HPO algorithms, including Bayesian optimization, multi-armed bandit. You can even integrate your own proprietary solution.
  - tristandeleu/pytorch-meta - loaders for few-shot learning & meta-learning in PyTorch. Torchmeta contains popular meta-learning benchmarks, fully compatible with both torchvision and PyTorch's DataLoader
  - learnables/learn2learn - learning Library for Researchers
  - dragonfly/Dragonfly
  - starlibs/AILibs - search): (AStar, BestFirst, Branch & Bound, DFS, MCTS, and more);2)Logic (jaicore-logic): Represent and reason about propositional and simple first order logic formulas;3)Planning (jaicore-planning): State-space planning (STRIPS, PDDL), and hierarchical planning (HTN, ITN, PTN);4)Reproducible Experiments (jaicore-experiments): Design and efficiently conduct experiments in a highly parallelized manner.;5)Automated Software Configuration (HASCO): Hierarchical configuration of software systems.;6)Automated Machine Learning (ML-Plan): Automatically find optimal machine learning pipelines in WEKA or sklearn
  - PGijsbers/gama - users and AutoML researchers. It generates optimized machine learning pipelines given specific input data and resource constraints. A machine learning pipeline contains data preprocessing (e.g. PCA, normalization) as well as a machine learning algorithm (e.g. Logistic Regression, Random Forests), with fine-tuned hyperparameter settings (e.g. number of trees in a Random Forest).To find these pipelines, multiple search procedures have been implemented. GAMA can also combine multiple tuned machine learning pipelines together into an ensemble, which on average should help model performance. At the moment, GAMA is restricted to classification and regression problems on tabular data. In addition to its general use AutoML functionality, GAMA aims to serve AutoML researchers as well. During the optimization process, GAMA keeps an extensive log of progress made. Using this log, insight can be obtained on the behaviour of the search procedure.
  - S
  - microsoft/EconML - of-the-art machine learning techniques with econometrics to bring automation to complex causal inference problems. The promise of EconML:1)Implement recent techniques in the literature at the intersection of econometrics and machine learning;2)Maintain flexibility in modeling the effect heterogeneity (via techniques such as random forests, boosting, lasso and neural nets), while preserving the causal interpretation of the learned model and often offering valid confidence intervals;3)Use a unified API;4)Build on standard Python packages for Machine Learning and Data Analysis.
  - Yelp/MOE - consuming or expensive
  - flytxtds/AutoGBT - drift. AutoGBT was developed by a joint team ('autodidact.ai') from Flytxt, Indian Institute of Technology Delhi and CSIR-CEERI as a part of NIPS 2018 AutoML Challenge (The 3rd AutoML Challenge: AutoML for Lifelong Machine Learning).
  - MainRo/xgbtune
  - autonomio/talos
  - HunterMcGushion/hyperparameter_hunter - term, persistent optimization that remembers all your tests. HyperparameterHunter provides a wrapper for machine learning algorithms that saves all the important data. Simplify the experimentation and hyperparameter tuning process by letting HyperparameterHunter do the hard work of recording, organizing, and learning from your tests — all while using the same libraries you already do. Don't let any of your experiments go to waste, and start doing hyperparameter optimization the way it was meant to be
  - ja-thomas/autoxgboost
  - ScottfreeLLC/AlphaPy - learn, pandas, and Keras libraries, as well as many other helpful libraries for feature engineering and visualization
  - gdikov/hypertunity - box hyperparameter optimisation.
  - laic-ufmg/recipe - based genetic programming
  - produvia/ai-platform - centered or task-focused machine learning models. These models, or AI services, solve distinct tasks or functions.Examples of AI tasks include:1)semantic segmentation (computer visions);2)machine translation (natural language processing);3)word embeddings (methodology);4)recommendation systems (miscellaneous);5)speech recognition (speech);6)atari games (playing games);7)link prediction (graphs);8)time series classification (time series);9)audio generation (audio);10)visual odometry (robots);11)music information retrieval (music);12)dimensionality reduction (computer code);13)decision making (reasoning);14)knowledge graphs (knowledge base);15)adversarial attack (adversarial).
  - wywongbd/autocluster
  - ksachdeva/scikit-nni - parameters in different environments like local machine, remote servers and cloud
  - SaltWaterStudio/modgen
  - gomerudo/automl
  - crawles/automl_service
  - ypeleg/HungaBunga - learn models and all scikit-learn parameters with fit predict
  - accurat/ackeras - Learn
  - bhat-prashant/reinforceML
  - reiinakano/Xcessive - based application for quick, scalable, and automated hyperparameter tuning and stacked ensembling in Python
  - minimaxir/automl-gs - gs is an AutoML tool which, unlike Microsoft's NNI, Uber's Ludwig, and TPOT, offers a zero code/model definition interface to getting an optimized model and data transformation pipeline in multiple popular ML/DL frameworks, with minimal Python dependencies (pandas + scikit-learn + your framework of choice). automl-gs is designed for citizen data scientists and engineers without a deep statistical background under the philosophy that you don't need to know any modern data preprocessing and machine learning engineering techniques to create a powerful prediction workflow
  - cc-hpc-itwm/PHS
  - tobegit3hub/advisor
  - HIPS/Spearmint
  - claesenm/Optunity
  - cmccarthy1/automl - world problems. In the absence of expert machine learning engineers this handles the following processes within a traditional workflow
  - zygmuntz/HyperBand
  - ClimbsRocks/auto_ml - time predictions in production.A quick overview of buzzwords, this project automates:1)Analytics (pass in data, and auto_ml will tell you the relationship of each variable to what it is you're trying to predict).2)Feature Engineering (particularly around dates, and NLP).3)Robust Scaling (turning all values into their scaled versions between the range of 0 and 1, in a way that is robust to outliers, and works with sparse data).4)Feature Selection (picking only the features that actually prove useful).5)Data formatting (turning a DataFrame or a list of dictionaries into a sparse matrix, one-hot encoding categorical variables, taking the natural log of y for regression problems, etc).6)Model Selection (which model works best for your problem- we try roughly a dozen apiece for classification and regression problems, including favorites like XGBoost if it's installed on your machine).7)Hyperparameter Optimization (what hyperparameters work best for that model).8)Big Data (feed it lots of data- it's fairly efficient with resources).9)Unicorns (you could conceivably train it to predict what is a unicorn and what is not).10)Ice Cream (mmm, tasty...).11)Hugs (this makes it much easier to do your job, hopefully leaving you more time to hug those those you care about).
  - jgreenemi/Parris
  - ziyuw/rembo - dimensions via random embedding.
  - kootenpv/xtoy
  - jesse-toftum/cash_ml - time predictions in production
  - CCQC/PES-Learn - Learn is a Python library designed to fit system-specific Born-Oppenheimer potential energy surfaces using modern machine learning models. PES-Learn assists in generating datasets, and features Gaussian process and neural network model optimization routines. The goal is to provide high-performance models for a given dataset without requiring user expertise in machine learning.
  - AlexIoannides/ml-workflow-automation
  - yeticloud/dama
  - lai-bluejay/diego - learn API glossary, using Bayesian optimization and genetic algorithm.
  - mb706/automlr - package for automatically configuring mlr machine learning algorithms so that they perform well. It is designed for simplicity of use and able to run with minimal user intervention
  - XanderHorn/autoML
  - DataSystemsGroupUT/SmartML - Package representing a meta learning-based framework for automated selection and hyperparameter tuning for machine learning algorithms. Being meta-learning based, the framework is able to simulate the role of the machine learning expert. In particular, the framework is equipped with a continuously updated knowledge base that stores information about the meta-features of all processed datasets along with the associated performance of the different classifiers and their tuned parameters. Thus, for any new dataset, SmartML automatically extracts its meta features and searches its knowledge base for the best performing algorithm to start its optimization process. In addition, SmartML makes use of the new runs to continuously enrich its knowledge base to improve its performance and robustness for future runs
  - PaddlePaddle/AutoDL - sourced AutoDl Design is one implementation of AutoDL technique.
  - linxihui/lazyML - parameters of a list of models simultaneously with parallel support. It also has functionality to give an unbiased performance estimate of the mpTune procedure. Currently, classification, regression and survival models are supported.
  - darvis-ai/Brainless
  - r-tensorflow/autokeras
  - IBM/AutoMLPipline.jl - in macro programming features of Julia to symbolically process, manipulate pipeline expressions, and makes it easy to discover optimal structures for machine learning prediction and classification.
  - SciML/ModelingToolkit.jl - informed machine learning and automated transformations of differential equations
  - SciML/DataDrivenDiffEq.jl
  - ClimbsRocks/machineJS - featured default process for machine learning- all the parts are here and have functional default values in place. Modify to your heart's delight so you can focus on the important parts for your dataset, or run it all the way through with the default values to have fully automated machine learning
  - automl-js/automl-js - learn library to give quite close, albeit somewhat smaller (at most 1 percent of classification accuracy on average) score.
  - duckladydinh/KotlinML
- Distributed Frameworks
  - UCBerkeley/MLBase - - MLlib, MLI, ML Optimizer. 1)ML Optimizer: This layer aims to automating the task of ML pipeline construction. The optimizer solves a search problem over feature extractors and ML algorithms included in MLI and MLlib. The ML Optimizer is currently under active development.2)MLI: An experimental API for feature extraction and algorithm development that introduces high-level ML programming abstractions. A prototype of MLI has been implemented against Spark, and serves as a testbed for MLlib.3)MLlib: Apache Spark's distributed ML library. MLlib was initially developed as part of the MLbase project, and the library is currently supported by the Spark community. Many features in MLlib have been borrowed from ML Optimizer and MLI, e.g., the model and algorithm APIs, multimodel training, sparse data support, design of local / distributed matrices, etc.
  - Databricks/AutoML
  - automl/bohb
  - ccnt-glaucus/glaucus - processing engines. For the non-data science professionals across the domain, help them get the benefits of powerful machine learning tools by a simple way.Our platform integrates many excellent data processing engines including Spark, Tensorflow, Scikit-learn, and we established a set of easy-to-use design process bases on them. The user only need to upload data, simple configuration, algorithm selection, and train the algorithm by automatic or manual parameter adjustment. The platform also provides a wealth of evaluation indicators for the training model, so that non-professionals can maximize the role of machine learning in their fields.
  - intel-analytics/analytics-zoo
  - databricks/automl-toolkit - level "default only" FamilyRunner to low-level APIs that allow for highly customizable workflows to be created for automated ML tuning and Inference
  - salesforce/TransmogrifAI - mŏgˈrə-fī) is an AutoML library written in Scala that runs on top of Apache Spark. It was developed with a focus on accelerating machine learning developer productivity through machine learning automation, and an API that enforces compile-time type-safety, modularity, and reuse. Through automation, it achieves accuracies close to hand-tuned models with almost 100x reduction in time.
  - hyperopt/Hyperopt - valued, discrete, and conditional dimensions.
  - nusdbsystem/singa-auto - AUTO is a distributed system that trains machine learning (ML) models and deploys trained models, built with ease-of-use in mind. To do so, it leverages on automated machine learning (AutoML).
  - DataSystemsGroupUT/D-SmartML - Of-The-Art data engineering techniques towards building an off the box machine learning solution.
  - AxeldeRomblay/MLBox - of-the-art algorithms such as LightGBM and XGBoost. It also supports model stacking, which allows you to combine an information ensemble of models to generate a new model aiming to have better performance than the individual models.
  - HDI-Project/ATM - Data Interaction (HDI) Project at MIT.
  - HDI-Project/ATMSeer - time through a multi-granularity visualization. In this instantiation, we build on top of the ATM AutoML system
  - logicalclocks/maggy - box functions on top of Apache Spark. Compared to existing frameworks, maggy is not bound to stage based optimization algorithms and therefore it is able to make extensive use of early stopping in order to achieve efficient resource utilization.
  - automl/HpBandSter
  - giantcroc/featuretoolsOnSpark - end architecture of featuretools,We mainly use Spark DataFrame to achieve faster feature generation process(speed up 10x+)
  - ray-project/ray
  - tqichun/distributed-SMAC3 - based Algorithm Configuration, forked by https://github.com/automl/SMAC3 This package is a re-implementation of the original SMAC tool (see reference below). However, the reimplementation slightly differs from the original SMAC. For comparisons against the original SMAC, we refer to a stable release of SMAC (v2) in Java which can be found [here](http://www.cs.ubc.ca/labs/beta/Projects/SMAC/).
  - pierre-chaville/automlk
  - takezoe/predictionio-template-automl
  - nginyc/rafiki - of-use in mind. To do so, it leverages on automated machine learning (AutoML).
benchmark
- Distributed Frameworks
Projects
- Distributed Frameworks
  - microsoft/forecasting
  - DeepWisdom/AutoDL-cn
  - xiaomi-automl/fairdarts
  - RasaHQ/rasa - and voice-based conversations. With Rasa, you can build contextual assistants on:1)Facebook Messenger;2)Slack;3)Google Hangouts;4)Webex Teams;5)Microsoft Bot Framework;6)Rocket.Chat;7)Mattermost;8)Telegram;9)Twilio;Your own custom conversational channels or voice assistants as:1)Alexa Skills;2;2)Google Home Actions
  - google-research/morphnet - structure learning problem. Specifically, activation sparsity is induced by adding regularizers that target the consumption of specific resources such as FLOPs or model size. When the regularizer loss is added to the training loss and their sum is minimized via stochastic gradient descent or a similar optimizer, the learning problem becomes a constrained optimization of the structure of the network, under the constraint represented by the regularizer. The method was first introduced in our CVPR 2018, paper "MorphNet: Fast & Simple Resource-Constrained Learning of Deep Network Structure".
  - kakaobrain/fast-autoaugment
  - naszilla/bananas - based encoding scheme to featurize the neural architectures that are used to train the neural network model. After training on just 200 architectures, we are able to predict the validation accuracy of new architectures to within one percent on average. The full NAS algorithm beats the state of the art on the NASBench and the DARTS search spaces. On the NASBench search space, BANANAS is over 100x more efficient than random search, and 3.8x more efficent than the next-best algorithm we tried. On the DARTS search space, BANANAS finds an architecture with a test error of 2.57%.
  - quark0/DARTS
  - microsoft/petridishnn
  - mit-han-lab/once-for-all
  - NoamRosenberg/autodeeplab
  - nextml/NEXT
  - developers-cosmos/ML-CICD-GitHubActions
  - lightforever/mlcomp
  - zhengying-liu/autodl - organized by ChaLearn, Google and 4Paradigm. Accepted at NeurIPS 2019.
  - e2its/gdayf-core
  - AutoViML/AutoViz
  - paypal/autskearn-zeroconf
  - mikewlange/KETTLE
  - Yatoom/Optimus
  - loaiabdalslam/AUL
  - AlexImb/automl-streams
  - Jwuthri/Mozinor
  - kakaobrain/autoclint
  - cmusatyalab/opentpod
  - pfnet-research/autpgbt-alt
  - arberzela/efficientnas
  - positron1/amlb
  - ealcobaca/pymfe
  - u1234x1234/AutoSpeech2020
  - mittajithendra/Automated-Machine-Learning
  - aiorhiroki/farmer - automatically
  - NCC-dev/farmer
  - DAI-Lab/cardea
  - datamllab/autokaggle
  - chasedehan/diaml
  - a-hanf/mlr3automl
  - A2Amir/Machine-Learning-Pipelines - learning workflows with pipelines using the dataset of corporate messaging as a case study
  - mattjhayes/amle
  - uncharted-distil/distil-auto-ml
  - MaximilianJohannesObpacher/automl_server
  - yangfenglong/mAML1.0
  - matheusccouto/autolearn
  - gabrieljaguiar/mtlExperiment
  - thomas-young-2013/soln-ml
  - rsheth80/pmf-automl
  - BeelGroup/auto-surprise
  - melodyguan/ENAS
  - renqianluo/NAO
  - laic-ufmg/automlc
  - knowledge-learning/hp-optimization
  - magnusax/magnusax/automl
  - nitishkthakur/nitishkthakur/automlib
  - DataSystemsGroupUT/iSmartML
  - udellgroup/Oboe
  - fillassuncao/automl-dsge
  - piyushpathak03/Automated-Machine-Learning
  - yaswanthpalaghat/Chatbot-using-machine-learning-and-flask
  - AnyObject/OAT - A fully automated trading platform with machine learning capabilities
  - jwmueller/KDD20-tutorial
  - mlaskowski17/Feature-Engineering
  - mstaddon/GraniteAI
  - EricCacciavillani/eFlow
  - htoukour/AutoML
  - aarontuor/antk
  - raalesir/automated_environment
  - CodeSpaceHQ/MENGEL
  - TrixiaBelleza/Automated-Text-Classification
  - TwoRavens/TwoRavensSolver
  - shoprunback/openflow
  - rahul1471/mlops
  - flaviassantos/dashboard
  - mattlm0831/AutoAI
  - RadheTians/Automated-Data-Augmentation-Software

Programming Languages

Python 91 Jupyter Notebook 10 R 4 Scala 4 Julia 3 C++ 2 Java 2 TeX 1 C 1 q 1

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Awesome

awesome-automl

Uncategorized

Uncategorized

Papers

SURVEY

blogs & articles & book

Libraries

Distributed Frameworks

benchmark

Distributed Frameworks

Projects

Distributed Frameworks