Causal Inference and Stable Learning

A tutorial at IJCAI-2020

Peng Cui(cuip@tsinghua.edu.cn), Tsinghua University, China

 

Abstract

Predicting future outcome values based on their observed features using a model estimated on a training data set is a common machine learning problem. Many learning algorithms have been proposed and shown to be successful when the test data and training data come from the same distribution. However, the best-performing models for a given distribution of training data typically exploit subtle statistical relationships among features, making them potentially more prone to prediction error when applied to test data whose distribution differs from that in training data. How to develop learning models that are stable and robust to shifts in data is of paramount importance for both academic research and real applications.

Causal inference, which refers to the process of drawing a conclusion about a causal connection based on the conditions of the occurrence of an effect, is a powerful statistical modeling tool for explanatory and stable learning. In this tutorial, we focus on causal inference and stable learning, aiming to explore causal knowledge from observational data to improve the interpretability and stability of machine learning algorithms. First, we will give an introduction to causal inference and introduce some recent data-driven approaches to estimate the causal effect from observational data, especially in high dimensional settings. Aiming to bridge the gap between causal inference and machine learning for stable learning, we first give the definition of stability and robustness of learning algorithms, then will introduce some recently stable learning algorithms for improving the stability and interpretability of prediction. Finally, we will discuss the applications and future directions of stable learning, and provide the benchmark for stable learning.

 

Tutorial Outline

The tutorial is planned for 1:45 hours and comprised of the following 4 sections.

  1. Causal Inference and Its Implication for Learning
  2. Learning Stability and Robustness
  3. Theory and Algorithms for Stable Learning
  4. Applications and Benchmarks

 

Tutors’ Short Bio and Expertise

Peng Cui is an Associate Professor in Tsinghua University. He got his PhD degree from Tsinghua University in 2010. His research interests include causal inference and stable learning, network representation learning, and human behavioral modeling. He has published more than 100 papers in prestigious conferences and journals in data mining and multimedia. His recent research won the IEEE Multimedia Best Department Paper Award, SIGKDD 2016 Best Paper Finalist, ICDM 2015 Best Student Paper Award, SIGKDD 2014 Best Paper Finalist, IEEE ICME 2014 Best Paper Award, ACM MM12 Grand Challenge Multimodal Award, and MMM13 Best Paper Award. He is the Associate Editors of IEEE TKDE, IEEE TBD, ACM TIST, and ACM TOMM, etc. He has served as program co-chair and area chair of several major machine learning and artificial intelligence conferences, such as IJCAI, AAAI, ACM CIKM, ACM Multimedia, etc.