In magnetic resonance imaging (MRI), several images can be obtained using different imaging settings (e.g. T1, T2, DWI, and Flair). These images have similar anatomical structures but are with different contrasts, which provide a wealth of information for diagnosis.

As a fundamental algorithm for collaborative processing over multi-agent systems, distributed consensus algorithm has been studied for optimizing its convergence rate. Due to the close analogy between the diffusion problem and the consensus algorithm, the previous trend in the literature is to transform the diffusion system from the spatially continuous domain into the spatially discrete one. 

Graph neural networks have emerged as a popular and powerful tool for learning hierarchical representation of graph data. In complement to graph convolution operators, graph pooling is crucial for extracting hierarchical representation of data in graph neural networks. However, most recent graph pooling methods still fail to efficiently exploit the geometry of graph data. In this paper, we propose a novel graph pooling strategy that leverages node affinity to improve the hierarchical representation learning of graph data. 

In order to perform network analysis tasks, representations that capture the most relevant information in the graph structure are needed. However, existing methods learn representations that cannot be interpreted in a straightforward way and that are relatively unstable to perturbations of the graph structure. We address these two limitations by proposing node2coords, a representation learning algorithm for graphs, which learns simultaneously a low-dimensional space and coordinates for the nodes in that space.