Contrastive Brain Network Learning via Hierarchical Signed Graph Pooling Model
This work addresses the challenge of extracting biomarkers from brain functional networks for clinical phenotypes and neurodegenerative diseases, offering an interpretable model that provides biological insights, though it is incremental in improving existing graph learning methods for a specific domain.
The authors tackled the problem of analyzing brain functional networks, which are signed graphs, by proposing an interpretable hierarchical signed graph representation learning model and a data augmentation strategy for contrastive learning, achieving superior performance in classification and regression tasks on HCP and OASIS datasets compared to state-of-the-art techniques.
Recently brain networks have been widely adopted to study brain dynamics, brain development and brain diseases. Graph representation learning techniques on brain functional networks can facilitate the discovery of novel biomarkers for clinical phenotypes and neurodegenerative diseases. However, current graph learning techniques have several issues on brain network mining. Firstly, most current graph learning models are designed for unsigned graph, which hinders the analysis of many signed network data (e.g., brain functional networks). Meanwhile, the insufficiency of brain network data limits the model performance on clinical phenotypes predictions. Moreover, few of current graph learning model is interpretable, which may not be capable to provide biological insights for model outcomes. Here, we propose an interpretable hierarchical signed graph representation learning model to extract graph-level representations from brain functional networks, which can be used for different prediction tasks. In order to further improve the model performance, we also propose a new strategy to augment functional brain network data for contrastive learning. We evaluate this framework on different classification and regression tasks using the data from HCP and OASIS. Our results from extensive experiments demonstrate the superiority of the proposed model compared to several state-of-the-art techniques. Additionally, we use graph saliency maps, derived from these prediction tasks, to demonstrate detection and interpretation of phenotypic biomarkers.