Open jexp opened 6 years ago
would be good for fraud detection - eg the canonical subgraph pattern, and then prob scored variation from the canonical pattern for all detected subgraphs
Hi , is anyone actively working on this ?
@MarcianoAvihay noone is working on this one at the moment. If you wanted to have a go at it and create a PR we'd be happy to review/accept it.
Identify recurring graph pattern structures
We can take some ideas from ParseMIS Their HPGraph has similarities to our Graph interface, and then we should be able to transfer the algorithms used.