AutoML System

Survey

• A curated list of automated machine learning papers, articles, tutorials, slides and projects(https://github.com/hibayesian/awesome-automl-papers)
• Taking human out of learning applications: A survey on automated machine learning.(https://arxiv.org/pdf/1810.13306.pdf)
  • Quanming, Y., Mengshuo, W., Hugo, J.E., Isabelle, G., Yi-Qi, H., Yu-Feng, L., Wei-Wei, T., Qiang, Y. and Yang, Y.
• AutoML Freiburg-Hannover(https://www.ml4aad.org/automl/)
• Survey on End-To-End Machine Learning Automation(https://arxiv.org/pdf/1906.02287.pdf)(https://github.com/DataSystemsGroupUT/AutoML_Survey)
• Design Automation for Efficient Deep Learning Computing(https://arxiv.org/pdf/1904.10616.pdf)(https://github.com/mit-han-lab/haq-release)
  • Han, Song, et al. (arXiv preprint arXiv:1904.10616 (2019))

AutoML Opensource Toolkit

• Swearingen, Thomas, et al. "ATM: A distributed, collaborative, scalable system for automated machine learning." 2017 IEEE International Conference on Big Data (Big Data). IEEE, 2017.(https://dai.lids.mit.edu/wp-content/uploads/2018/02/atm_IEEE_BIgData-9-1.pdf)(https://github.com/HDI-Project/ATM)
• Google vizier: A service for black-box optimization.(https://ai.google/research/pubs/pub46180.pdf)(https://github.com/tobegit3hub/advisor)
  • Golovin, Daniel, et al. (SIGMOD 2017)
• Aut-sklearn: Automated Machine Learning with scikit-learn(https://github.com/automl/auto-sklearn)(https://papers.nips.cc/paper/5872-efficient-and-robust-automated-machine-learning.pdf)
• Katib: A Distributed General AutoML Platform on Kubernetes(https://github.com/kubeflow/katib/)(https://www.usenix.org/system/files/opml19papers-zhou.pdf)
• NNI: An open source AutoML toolkit for neural architecture search and hyper-parameter tuning(https://github.com/Microsoft/nni)
• AutoKeras: Accessible AutoML for deep learning.(https://github.com/keras-team/autokeras)
• Facebook/Ax: 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.(https://github.com/facebook/Ax)
• DeepSwarm: DeepSwarm is an open-source library which uses Ant Colony Optimization to tackle the neural architecture search problem.(https://github.com/Pattio/DeepSwarm)
• Google/AdaNet: AdaNet is a lightweight TensorFlow-based framework for automatically learning high-quality models with minimal expert. 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.(https://github.com/tensorflow/adanet)
• TransmogrifAI (pronounced trăns-mŏgˈrə-fī) is an AutoML library for building modular, reusable, strongly typed machine learning workflows on Apache Spark with minimal hand-tuning(https://github.com/salesforce/TransmogrifAI)
• Angel-ML/automl:An automatic machine learning toolkit, including hyper-parameter tuning and feature engineering.(https://github.com/Angel-ML/automlI)

Auto Model Selection

• Automating model search for large scale machine learning(https://amplab.cs.berkeley.edu/wp-content/uploads/2015/07/163-sparks.pdf)
  • Sparks, E.R., Talwalkar, A., Haas, D., Franklin, M.J., Jordan, M.I. and Kraska, T., 2015, August.
  • In Proceedings of the Sixth ACM Symposium on Cloud Computing (pp. 368-380). ACM.
• A framework for searching a predictive model(https://arxiv.org/pdf/1908.10310.pdf)
  • Takahashi, Yoshiki, Masato Asahara, and Kazuyuki Shudo
  • In SysML Conference, vol. 2018. 2018.
• Dynamic Autoselection and Autotuning of Machine Learning Models for Cloud Network Analytics(https://ieeexplore.ieee.org/document/8500348)
  • IEEE Transactions on Parallel and Distributed Systems 30, no. 5 (2018): 1052-1064.
  • Karn, Rupesh Raj, Prabhakar Kudva, and Ibrahim Abe M. Elfadel.