AUTOMATED SELF-SUPERVISED LEARNING FOR GRAPHS

Document Type

Conference Proceeding

Publication Date

1-1-2022

Abstract

Graph self-supervised learning has gained increasing attention due to its capacity to learn expressive node representations. Many pretext tasks, or loss functions have been designed from distinct perspectives. However, we observe that different pretext tasks affect downstream tasks differently across datasets, which suggests that searching over pretext tasks is crucial for graph self-supervised learning. Different from existing works focusing on designing single pretext tasks, this work aims to investigate how to automatically leverage multiple pretext tasks effectively. Nevertheless, evaluating representations derived from multiple pretext tasks without direct access to ground truth labels makes this problem challenging. To address this obstacle, we make use of a key principle of many real-world graphs, i.e., homophily, or the principle that “like attracts like,” as the guidance to effectively search various self-supervised pretext tasks. We provide theoretical understanding and empirical evidence to justify the flexibility of homophily in this search task. Then we propose the AUTOSSL framework to automatically search over combinations of various self-supervised tasks. By evaluating the framework on 8 real-world datasets, our experimental results show that AUTOSSL can significantly boost the performance on downstream tasks including node clustering and node classification compared with training under individual tasks.

Identifier

85128520222 (Scopus)

Publication Title

Iclr 2022 10th International Conference on Learning Representations

This document is currently not available here.

Share

COinS