Exploring Correlations of Self-Supervised Tasks for Graphs
This work addresses the problem of improving graph self-supervised learning for researchers and practitioners by providing insights into task correlations, though it appears incremental as it builds on existing multi-task learning approaches.
The paper tackles the limited understanding of relationships between self-supervised tasks in graph learning by defining correlation values to quantify these relationships, revealing complexities and limitations in existing methods, and proposes GraphTCM to enhance training, which significantly outperforms existing methods in downstream tasks.
Graph self-supervised learning has sparked a research surge in training informative representations without accessing any labeled data. However, our understanding of graph self-supervised learning remains limited, and the inherent relationships between various self-supervised tasks are still unexplored. Our paper aims to provide a fresh understanding of graph self-supervised learning based on task correlations. Specifically, we evaluate the performance of the representations trained by one specific task on other tasks and define correlation values to quantify task correlations. Through this process, we unveil the task correlations between various self-supervised tasks and can measure their expressive capabilities, which are closely related to downstream performance. By analyzing the correlation values between tasks across various datasets, we reveal the complexity of task correlations and the limitations of existing multi-task learning methods. To obtain more capable representations, we propose Graph Task Correlation Modeling (GraphTCM) to illustrate the task correlations and utilize it to enhance graph self-supervised training. The experimental results indicate that our method significantly outperforms existing methods across various downstream tasks.