Wei Jin, Xiaorui Liu, Xiaoyu Zhao, Yao Ma, Neil Shah, Jiliang Tang

Research output: Contribution to conferencePaperpeer-review

15 Scopus citations


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.

Original languageEnglish (US)
StatePublished - 2022
Event10th International Conference on Learning Representations, ICLR 2022 - Virtual, Online
Duration: Apr 25 2022Apr 29 2022


Conference10th International Conference on Learning Representations, ICLR 2022
CityVirtual, Online

All Science Journal Classification (ASJC) codes

  • Language and Linguistics
  • Computer Science Applications
  • Education
  • Linguistics and Language


Dive into the research topics of 'AUTOMATED SELF-SUPERVISED LEARNING FOR GRAPHS'. Together they form a unique fingerprint.

Cite this