US 11,853,882 B2
Methods, apparatus, and storage medium for classifying graph nodes
Wenbing Huang, Shenzhen (CN); Yu Rong, Shenzhen (CN); and Junzhou Huang, Shenzhen (CN)
Assigned to TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed by TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED, Shenzhen (CN)
Filed on Jan. 20, 2021, as Appl. No. 17/153,014.
Application 17/153,014 is a continuation of application No. PCT/CN2019/117173, filed on Nov. 11, 2019.
Claims priority of application No. 201811361409.0 (CN), filed on Nov. 15, 2018.
Prior Publication US 2021/0142108 A1, May 13, 2021
Int. Cl. G06F 18/213 (2023.01); G06N 3/08 (2023.01); G06F 18/214 (2023.01); G06F 18/2413 (2023.01); G06N 7/01 (2023.01)
CPC G06N 3/08 (2013.01) [G06F 18/213 (2023.01); G06F 18/214 (2023.01); G06F 18/24147 (2023.01); G06N 7/01 (2023.01)] 17 Claims
OG exemplary drawing
 
1. A method for training a node classification model, the method comprising:
obtaining, by a device comprising a memory storing instructions and a processor in communication with the memory, a target node subset and a neighbor node subset corresponding to the target node subset from a sample node set labeled with a target node class, a neighbor node in the neighbor node subset being associated with a target node in the target node subset;
extracting, by the device, a feature subset of the target node subset based on the neighbor node subset by using a node classification model, the feature subset comprising a feature vector of the target node;
performing, by the device, class prediction for the target node subset according to the feature subset, to obtain a predicted class probability subset; and
training, by the device, the node classification model with a target model parameter according to the predicted class probability subset and a target node class subset of the target node subset, by:
determining, by the device, a target loss value according to the predicted class probability subset and the target node class subset of the target node subset;
determining, by the device, a model parameter gradient according to the target loss value; and
training, by the device, the node classification model with the target model parameter according to the model parameter gradient.