US 12,175,366 B2
Graph neural networks for datasets with heterophily
Ryan Rossi, Santa Clara, CA (US); Tung Mai, San Jose, CA (US); Nedim Lipka, Campbell, CA (US); Jiong Zhu, Ann Arbor, MI (US); Anup Rao, San Jose, CA (US); and Viswanathan Swaminathan, Saratoga, CA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Mar. 23, 2021, as Appl. No. 17/210,157.
Prior Publication US 2022/0309334 A1, Sep. 29, 2022
Int. Cl. G06N 3/08 (2023.01); G06F 16/901 (2019.01); G06F 18/2132 (2023.01); G06F 18/2413 (2023.01); G06N 5/02 (2023.01)
CPC G06N 3/08 (2013.01) [G06F 16/9024 (2019.01); G06F 18/21322 (2023.01); G06F 18/24147 (2023.01); G06N 5/02 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method that includes performing, with one or more processing devices, operations comprising:
receiving a dataset including a graph data structure;
processing, with a graph neural network, the dataset to generate a new graph data structure, wherein processing the graph neural network includes, at least:
defining a set of prior belief vectors respectively corresponding to nodes of the graph data structure,
applying a parameterized compatibility matrix to a node of the graph neural network to propagate a characteristic of a belief vector corresponding to the node to nodes within a neighborhood of the node,
performing echo cancelation to prevent the characteristic from being subsequently propagated back to the node while executing, using the parameterized compatibility matrix to model a probability of nodes of different classes being connected, a compatibility-guided propagation from the set of prior belief vectors,
predicting, by the graph neural network, a class label for the node of the graph data structure based on the compatibility-guided propagations and a characteristic of at least one node within the neighborhood of the node, and
assigning the class label to the node; and
outputting, using the class label, the new graph data structure, wherein the new graph data structure is usable by a software tool for modifying an operation of a computing environment.