FLAML/tutorials/flaml-tutorial-kdd-22.md

KDD 2022 Hands-on Tutorial - Automated Machine Learning & Tuning with FLAML

Session Information

Date: August 16, 2022 Time: 9:30 AM ET Location: 101 Duration: 3 hours

For the most up-to-date information, see the SIGKDD'22 Program Agenda

Tutorial Slides

What Will You Learn?

• What FLAML is and how to use it to find accurate ML models with low computational resources for common machine learning tasks
• How to leverage the flexible and rich customization choices to:
  • Finish the last mile for deployment
  • Create new applications
• Code examples, demos, and use cases
• Research & development opportunities

Session Agenda

Part 1

• Overview of AutoML and FLAML
• Task-oriented AutoML with FLAML
  • Notebook: A classification task with AutoML; Open In Colab
  • Notebook: A regression task with AuotML using LightGBM as the learner; Open In Colab
• ML.NET demo
• Tune user defined functions with FLAML
  • Notebook: Basic tuning procedures and advanced tuning options; Open In Colab
  • Notebook: Tune pytorch; Open In Colab
• Q & A

Part 2

• Zero-shot AutoML
  • Notebook: Zeroshot AutoML; Open In Colab
• Time series forecasting
  • Notebook: AutoML for Time Series Forecast tasks; Open In Colab
• Natural language processing
  • Notebook: AutoML for NLP tasks; Open In Colab
• Online AutoML
  • Notebook: Online AutoML with Vowpal Wabbit; Open In Colab
• Fair AutoML
• Challenges and open problems