Pre-train Graph Neural Networks for Brain Network Analysis

Yi Yang, Hejie Cui, Carl Yang

Abstract: Human brains, controlling behaviors and cognition, are at the center of complex neurobiological systems. Recent studies in neuroscience and neuroimaging analysis have reached a consensus that interactions among brain regions of interest (ROIs) are driving factors for neural development and disorders. Graph neural networks as a powerful tool for analyzing graph-structured data are naturally applied to the analysis of brain networks. However, training of deep learning models including GNNs often requires a significant amount of labeled data. Due to the complicated data acquisition process and restrictions on data sharing, brain network datasets are still small compared to other domains (e.g., molecules, proteins). Moreover, real clinical tasks (e.g., mental disorder analysis) are often conducted on local datasets with even smaller scales and larger noises. To this end, we propose to leverage pre-training to capture the intrinsic brain network structures regardless of specific clinical outcomes. Specifically, we characterize the contributions in this work from two perspectives: (1) We design brain-network-oriented unsupervised pre-training techniques to utilize large-scale brain imaging studies without highly relevant task labels. (2) To facilitate effective knowledge transfer across studies with different ROI systems, we propose to develop a data-driven parcellation atlas mapping pipeline. The proposed pre-training techniques are validated with various GNN models. Extensive experiments demonstrate consistent improvement in performance as well as robustness.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Machine Learning for Sciences (eg biology, physics, health sciences, social sciences, climate/sustainability )