A framework for analyzing single-cell genomics data, in which geometrical properties are harnessed to obtain insights on cellular diversity, including precise clustering, clear visualizations, and ...

Want more charts like these? See our charts on the secrets of the jobless recovery, the richest 1 percent of Americans, and how the superwealthy beat the IRS. How Rich Are the Superrich? A huge share ...

Abstract: Traditional shortest-path graph kernels generate for each graph a histogram-like feature map, whose elements represent the number of occurrences of non-isomorphic shortest paths in this ...

Abstract: Graph neural networks (GNNs) excel in graph representation learning by integrating graph structure and node features. Existing GNNs, unfortunately, fail to account for the uncertainty of ...

TLDR: We study the architecture of neural networks through the lens of network science, and discover that good neural networks are alike in terms of their underlying graph structure. Overview of our ...

Prerequisites: Graduate standing or consent of instructor. Many students find this course difficult, so a first-rate math background is highly recommended. See the Review Sheet for material you're ...

Our software paper and benchmark paper are publicly available. If you use PyGOD or BOND in a scientific publication, we would appreciate citations to the following papers: @article{JMLR:v25:23-0963, ...

Spinal cord injury (SCI) may lead to impaired motor function, autonomic nervous system dysfunction, and other dysfunctions. Brain-computer Interface (BCI) system based on motor imagery (MI) can ...

We apologize that the Science NetLinks website is unavailable. Unfortunately, the server and website became unstable and a security risk so the website needed to be taken down immediately. We ...

Composed of nodes and edges, graph structured data are organized in the non-Euclidean geometric space and ubiquitous especially in chemical compounds, proteins, etc. They usually contain rich ...