18334735. HETEROGENEOUS GRAPH LEARNING-BASED UNIFIED NETWORK REPRESENTATION (Cisco Technology, Inc.)
Contents
HETEROGENEOUS GRAPH LEARNING-BASED UNIFIED NETWORK REPRESENTATION
Organization Name
Inventor(s)
Qihong Shao of Clyde Hill WA (US)
David C. White, Jr. of St. Petersburg FL (US)
HETEROGENEOUS GRAPH LEARNING-BASED UNIFIED NETWORK REPRESENTATION
This abstract first appeared for US patent application 18334735 titled 'HETEROGENEOUS GRAPH LEARNING-BASED UNIFIED NETWORK REPRESENTATION
Original Abstract Submitted
A heterogeneous graph learning system generates and analyzes network implementations. The heterogeneous graph learning system includes obtaining information describing multiple network implementations including heterogeneous nodes. The heterogeneous graph learning system also includes generating a one-hop graph connecting a particular node of the heterogeneous nodes with a set of related nodes. The one-hop graph connects the particular node with the set of related nodes via corresponding edges. The heterogeneous graph learning system further includes transforming the one-hop graph into a weighted graph based on a Dynamic Meta Path Transformation (DMPT). In the DMPT, each of the corresponding edges connecting the particular node to a corresponding related node among the set of related nodes is associated with a corresponding weight.
