Multi-modal Multi-kernel Graph Learning for Autism Prediction and Biomarker Discovery

Multi-modal integration and classification based on graph learning is among the most challenging obstacles in disease prediction due to its complexity. Several recent works on the basis of attentional mechanisms have been proposed to disentangle the problem of multi-modal integration. However, there are certain limitations to these techniques. Primarily, these works focus on explicitly integrating at the feature level using weight scores, which cannot effectively address the negative impact between modalities. Next, a majority of them utilize single-sized filters to extract graph features, ignoring the heterogeneous information over graphs. To overcome these drawbacks, we propose MMKGL (Multi-modal Multi-Kernel Graph Learning). For the problem of negative impact between modalities, we use the multi-modal graph embedding module to construct a multi-modal graph. Different from the traditional manual construction of static graphs, a separate graph is generated for each modality by graph adaptive learning, where a function graph and a supervision graph are introduced for optimiztion during the multi-graph fusion embedding process. We then apply the multi-kernel graph learning module to extract heterogeneous information from the multi-modal graph. The information in the multi-modal graph at different levels is aggregated by convolutional kernels with different receptive field sizes, followed by generating a cross-kernel discovery tensor for disease prediction. Our method is evaluated on the benchmark Autism Brain Imaging Data Exchange (ABIDE) dataset and outperforms the state-of-the-art methods. In addition, discriminative brain regions associated with autism are identified by our model, providing guidance for the study of autism pathology.