## Tutorial Description

Graph machine learning has been extensively studied in both academia and industry. Although booming with a vast number of emerging methods and techniques, most of the literature is built on the in-distribution (I.D.) hypothesis, i.e., testing and training graph data are sampled from the identical distribution. However, this I.D. hypothesis can hardly be satisfied in many real-world graph scenarios where the model performance substantially degrades when there exist distribution shifts between testing and training graph data. To solve this critical problem, out-of-distribution (OOD) generalization on graphs, which goes beyond the I.D. hypothesis, has made great progress and attracted ever-increasing attention from the research community. This tutorial is to disseminate and promote the recent research achievement on out-of-distribution generalization on graphs, which is an exciting and fast-growing research direction in the general field of machine learning and data mining. We will advocate novel, high-quality research findings, as well as innovative solutions to the challenging problems in out-of-distribution generalization and its applications on graphs. This topic is at the core of the scope of The Web Conference, and is attractive to machine learning as well as data mining audience from both academia and industry.

## Tutorial Outline

To the best of our knowledge, this tutorial is the first to systematically and comprehensively discuss out-of-distribution generalization on graphs, with a great potential to draw a large amount of interests in the community. The tutorial is planned for 1:45h (on Aug. 19) and organized into 4 sections.

## Target Audience and Prerequisites

This tutorial will be highly accessible to the whole machine learning and data mining community, including researchers, students and practitioners who are interested in disentangled representation learning, causal inference, self-supervised learning, invariant learning and their applications in graph related tasks. The tutorial will be self-contained and designed for introductory and intermediate audiences. No special prerequisite knowledge is required to attend this tutorial.

## Motivation, Relevance and Rationale

Out-of-distribution generalization on graphs is becoming a hot research topic in both academia and industry. This tutorial is to disseminate and promote the recent research achievements on out-of-distribution generalization on graphs, which is an exciting and fast-growing research direction in the general field of machine learning and graph neural network. We will advocate novel, high-quality research findings, as well as innovative solutions to the challenging problems in out-of-distribution generalization on graphs. This topic is at the core of the scope of The Web Conference, and is attractive to The Web Conference audience from both academia and industry.

## Tutorial Overview

Many graph machine learning algorithms or graph neural networks have been proposed and shown to be successful when the test graph data and training graph data come from the same distribution. However, the best-performing graph 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 graph learning models that are stable and robust to shifts in data is of paramount importance for both academic research and real applications.

In this tutorial, we discuss promising solutions to out-of-distribution generalization problem from two aspects:

### Out-of-distribution generalized graph model

Disentangled graph representation learning aims to learn representations that separate these distinct and informative factors behind the graph data and characterize these factors in different parts of the factorized vector representations. Such representations have been demonstrated to be more resilient to the complex variants, and able to benefit OOD generalization. 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 disentanglement and causal inference inspired graph models, aiming to explore informative independent latent factors and causal knowledge from observational graph data to improve the interpretability and stability of graph machine learning algorithms. We will give an introduction to disentanglement and causal inference, and introduce some recent representative approaches to produce OOD generalized graph representations.

### Out-of-distribution generalized graph training strategy

Besides Out-of-distribution generalized graph model, some works focus on exploiting training schemes with tailored optimization objectives and constraints to promote OOD generalization on graphs, including graph invariant learning, graph adversarial training, and graph self-supervised learning. Some graph invariant learning methods are built upon the invariance principle to address the OOD generalization problem from a principle way, which aim to exploit the invariant relationships between features and labels across different distributions while disregarding the variant spurious correlations. Some graph adversarial training and graph self-supervised learning methods have also been demonstrated to improve graph model robustness against distribution shifts and OOD generalization ability. We will give an introduction to these graph training strategies and introduce some recent approaches for handling OOD generalization.

The tutorial will be presented lively. However, in case of any technical problems, we may also provide a pre-recorded video for the tutorial.