KDD Papers

Structural Deep Brain Network Mining

Shen Wang (University of Illinois at Chicago);Lifang He (University of Illinois at Chicago);Bokai Cao (University of Illinois at Chicago);Chun-Ta Lu (University of Illinois at Chicago);Philip Yu (University of Illinois at Chicago);Ann Ragin (Northwestern University)


Mining from neuroimaging data is becoming increasingly popular in the field of healthcare and bioinformatics, due to its potential to discover clinically meaningful structure patterns that could facilitate the understanding and diagnosis of neurological and neuropsychiatric disorders. Most recent researches concentrate on applying subgraph mining techniques to discover connected subgraph patterns in the brain network. However, the underlying brain network structure is complicated. As a shallow linear model, subgraph mining can not capture the highly non-linear structures, resulting in sub-optimal patterns. Therefore, how to learn representations that can capture the highly non-linearity of brain networks and preserve the underlying structures is a critical problem. In this paper, we propose a Structural Deep Brain Network mining method, namely SDBN, to learn highly non-linear and structure-preserving representations of brain networks. Specifically, we first introduce a novel graph normalization approach based on module identification, which rearranges the order of the nodes to preserve the modular structure of the graph.Next, we perform structural augmentation to further enhance the spatial information of the normalized graph. Then we propose a deep feature learning framework for combining supervised learning and unsupervised learning in a small-scale setting, by augmenting Convolutional Neural Network (CNN) with decoding pathways for reconstruction. With the help of the multiple layers of non-linear mapping, the proposed SDBN approach can capture the highly non-linear structure of brain networks. Besides, it has better generalization capability for high-dimensional brain network and is suitable for small sample learning. To evaluate the proposed SDBN method , we conduct extensive experiments on four real brain network datasets for disease diagnoses. The experiment results show that SDBN can capture discriminative and meaningful structural graph representations for brain disorder diagnosis.