AutoML: From Methodology to Application

Abstract

Machine Learning methods have been adopted for a wide range of real-world applications, ranging from social networks, online image/video-sharing platforms, and e-commerce to education, healthcare, etc. However, in practice, a large amount of effort is required to tune several components of machine learning methods, including data representation, hyperparameter, and model architecture, in order to achieve a good performance. To alleviate the required tunning efforts, Automated Machine Learning (AutoML), which can automate the process of applying machine learning methods, has been studied in both academy and industry recently. In this tutorial, we will introduce the main research topics of AutoML, including Hyperparameter Optimization, Neural Architecture Search, and Meta-Learning. Two emerging topics of AutoML, Automatic Feature Generation and Machine Learning Guided Database, will also be discussed since they are important components for real-world applications. For each topic, we will motivate it with application examples from industry, illustrate the state-of-the-art methodologies, and discuss some future research directions based on our experience from industry and the trends in academy.

Tutorial Slides

slides.pdf

Schedule

Date: Nov 5th (UTC)

• 5:00AM–5:10AM Welcome from Organizers (by Yaliang Li)
• 5:10AM–5:40AM Hyperparameter Optimization (HPO) (by Yaliang Li)
• 5:40AM–6:15AM Neural Architecture Search (NAS) (by Zhen Wang)
• 6:15AM–6:30AM Meta-learning (by Zhen Wang)
• 6:30AM–7:00AM Auto Feature Generation (by Yuexiang Xie)
• 7:00AM–7:25AM End-to-End AutoML (by Ce Zhang)
• 7:25AM–7:50AM ML-Guided Database: Learned Index (by Bolin Ding)
• 7:50AM–9:50AM ML-Guided Database: Cardinality Estimation (by Rong Zhu and Kai Zeng)
• 9:50AM–9:55AM AutoML Tools (by Zhen Wang)
• 9:55AM–10:00AM Closing Remarks (by Yaliang Li)

Or equivalently, for the convenience of audiences in China, Singapore, Australian, etc., Nov 5th (UTC+8)

• 13:00PM–13:10PM Welcome from Organizers (by Yaliang Li)
• 13:10PM–13:40PM Hyperparameter Optimization (HPO) (by Yaliang Li)
• 13:40PM–14:15PM Neural Architecture Search (NAS) (by Zhen Wang)
• 14:15PM–14:30PM Meta-learning (by Zhen Wang)
• 14:30PM–15:00PM Auto Feature Generation (by Yuexiang Xie)
• 15:00PM–15:25PM End-to-End AutoML (by Ce Zhang)
• 15:25PM–15:50PM ML-Guided Database: Learned Index (by Bolin Ding)
• 15:50PM–17:50PM ML-Guided Database: Cardinality Estimation and Query Optimizer (by Rong Zhu and Kai Zeng)
• 17:50PM–17:55PM AutoML Tools (by Zhen Wang)
• 17:55PM–18:00PM Closing Remarks (by Yaliang Li)

Organizers

Yaliang Li	Zhen Wang	Yuexiang Xie	Bolin Ding	Kai Zeng	Ce Zhang	Rong Zhu