公开(公告)号：US20220019410A1

公开(公告)日：2022-01-20

申请号：US16946982

申请日：2020-07-14

Applicant: X Development LLC

Inventor： Catalina Codruta Cangea ,  Qianyu Zhang

IPC: G06F8/33 ,  G06N20/00 ,  G06N5/04

Abstract: Implementations are described herein for training and using machine learning to determine mappings between matching nodes of graphs representing predecessor source code snippets and graphs representing successor source code snippets. In various implementations, first and second graphs may be obtained, wherein the first graph represents a predecessor source code snippet and the second graph represents a successor source code snippet. The first graph and the second graph may be applied as inputs across a trained machine learning model to generate node similarity measures between individual nodes of the first graph and nodes of the second graph. Based on the node similarity measures, a mapping may be determined across the first and second graphs between pairs of matching nodes.

公开(公告)号：US11340873B2

公开(公告)日：2022-05-24

申请号：US16946982

申请日：2020-07-14

Applicant: X Development LLC

Inventor： Catalina Codruta Cangea ,  Qianyu Zhang

IPC: G06N20/00 ,  G06F8/33 ,  G06N5/04

Abstract: Implementations are described herein for training and using machine learning to determine mappings between matching nodes of graphs representing predecessor source code snippets and graphs representing successor source code snippets. In various implementations, first and second graphs may be obtained, wherein the first graph represents a predecessor source code snippet and the second graph represents a successor source code snippet. The first graph and the second graph may be applied as inputs across a trained machine learning model to generate node similarity measures between individual nodes of the first graph and nodes of the second graph. Based on the node similarity measures, a mapping may be determined across the first and second graphs between pairs of matching nodes.