Learnable Pooling in Graph Convolution Networks for Brain Surface Analysis
This work addresses brain surface analysis for neuroscience by introducing a flexible pooling technique, though it is incremental as it builds on existing graph convolution methods.
The paper tackled the problem of analyzing brain surface data with graph convolutional networks by proposing a learnable pooling method that aggregates graph nodes based on spectral embedding, resulting in improved state-of-the-art performance on tasks like Alzheimer's disease classification and brain age regression across multiple benchmark datasets.
Brain surface analysis is essential to neuroscience, however, the complex geometry of the brain cortex hinders computational methods for this task. The difficulty arises from a discrepancy between 3D imaging data, which is represented in Euclidean space, and the non-Euclidean geometry of the highly-convoluted brain surface. Recent advances in machine learning have enabled the use of neural networks for non-Euclidean spaces. These facilitate the learning of surface data, yet pooling strategies often remain constrained to a single fixed-graph. This paper proposes a new learnable graph pooling method for processing multiple surface-valued data to output subject-based information. The proposed method innovates by learning an intrinsic aggregation of graph nodes based on graph spectral embedding. We illustrate the advantages of our approach with in-depth experiments on two large-scale benchmark datasets. The flexibility of the pooling strategy is evaluated on four different prediction tasks, namely, subject-sex classification, regression of cortical region sizes, classification of Alzheimer's disease stages, and brain age regression. Our experiments demonstrate the superiority of our learnable pooling approach compared to other pooling techniques for graph convolution networks, with results improving the state-of-the-art in brain surface analysis.