Abstract: Various embodiments describe techniques for making inferences from graph-structured data using graph convolutional networks (GCNs). The GCNs use various pre-defined motifs to filter and select adjacent nodes for graph convolution at individual nodes, rather than merely using edge-defined immediate-neighbor adjacency for information integration at each node. In certain embodiments, the graph convolutional networks use attention mechanisms to select a motif from multiple motifs and select a step size for each respective node in a graph, in order to capture information from the most relevant neighborhood of the respective node.

Abstract: Various embodiments describe techniques for making inferences from graph-structured data using graph convolutional networks (GCNs). The GCNs use various pre-defined motifs to filter and select adjacent nodes for graph convolution at individual nodes, rather than merely using edge-defined immediate-neighbor adjacency for information integration at each node. In certain embodiments, the graph convolutional networks use attention mechanisms to select a motif from multiple motifs and select a step size for each respective node in a graph, in order to capture information from the most relevant neighborhood of the respective node.

Abstract: Various embodiments describe techniques for making inferences from graph-structured data using graph convolutional networks (GCNs). The GCNs use various pre-defined motifs to filter and select adjacent nodes for graph convolution at individual nodes, rather than merely using edge-defined immediate-neighbor adjacency for information integration at each node. In certain embodiments, the graph convolutional networks use attention mechanisms to select a motif from multiple motifs and select a step size for each respective node in a graph, in order to capture information from the most relevant neighborhood of the respective node.

Abstract: A special purpose VideoPhone terminal combines a desk, telephone and display in a non-threatening manner. The desk may accommodate users may may be confined to a wheelchair or need extra leg room. The telephone is, or either is disguised as a less-menacing-looking telephone. The VideoPhone terminal provides a local participant with a near real-time motion image of the remote participant on what appears to be a television screen but is actually a touch screen. The local user interacts with the VideoPhone system using the touch-tone buttons on the telephone and/or by actuating predefined hotspots on television-like screen. Additionally, the screen is subdivided into separate frames for still and motion images when in use as a videophone. Frames around the real-time motion and/or still images are also active hotspots which control video attributes of the image displayed or to be displayed within the frame and act as a printing control for printing the image.