Figure 3 - uploaded by Yaxin Cui
Content may be subject to copyright.
Download
View publication
AUC-ROC curve to predict 2014 coconsideration network with 6 attributes and 29 attributes

AUC-ROC curve to predict 2014 coconsideration network with 6 attributes and 29 attributes

Source publication
Figure 2: Illustration of sampling and aggregation in GraphSAGE method....
Figure 3: AUC-ROC curve to predict 2014 coconsideration network with 6...
Comparison of this work with prior studies on modeling car relationship...
Confusion matrix in predicting 2014 with six features and 296 cars for...
A Graph Neural Network Approach for Product Relationship Prediction
Preprint
Full-text available
  • May 2021
Graph Neural Networks have revolutionized many machine learning tasks in recent years, ranging from drug discovery, recommendation systems, image classification, social network analysis to natural language understanding. This paper shows their efficacy in modeling relationships between products and making predictions for unseen product networks. By...
Cite
Download full-text

Contexts in source publication

Context 1
... fed into the GNN model and followed by the classification model, the link existence of each pair of nodes is forecasted with a certain probability threshold. Likewise, we computed the confusion matrix for the predicted 2014 co-consideration network in Ta- ble 3,and calculated the F1 score as 0.65. Furthermore, we scoped out the AUC-ROC curve (in Fig. 3) at various threshold settings. The overall AUC is 0.80. Table 3 and Fig. 3, where the F1 score is 0.65 and AUC is 0.80. Compared to the prediction results in 2014, the prediction in 2015 maintains an equivalent performance, which is an indication of model ...
Context 2
... of each pair of nodes is forecasted with a certain probability threshold. Likewise, we computed the confusion matrix for the predicted 2014 co-consideration network in Ta- ble 3,and calculated the F1 score as 0.65. Furthermore, we scoped out the AUC-ROC curve (in Fig. 3) at various threshold settings. The overall AUC is 0.80. Table 3 and Fig. 3, where the F1 score is 0.65 and AUC is 0.80. Compared to the prediction results in 2014, the prediction in 2015 maintains an equivalent performance, which is an indication of model ...
Context 3
... fed into the GNN model and followed by the classification model, the link existence of each pair of nodes is forecasted with a certain probability threshold. Likewise, we computed the confusion matrix for the predicted 2014 co-consideration network in Ta- ble 3,and calculated the F1 score as 0.65. Furthermore, we scoped out the AUC-ROC curve (in Fig. 3) at various threshold settings. The overall AUC is 0.80. Table 3 and Fig. 3, where the F1 score is 0.65 and AUC is 0.80. Compared to the prediction results in 2014, the prediction in 2015 maintains an equivalent performance, which is an indication of model ...
Context 4
... of each pair of nodes is forecasted with a certain probability threshold. Likewise, we computed the confusion matrix for the predicted 2014 co-consideration network in Ta- ble 3,and calculated the F1 score as 0.65. Furthermore, we scoped out the AUC-ROC curve (in Fig. 3) at various threshold settings. The overall AUC is 0.80. Table 3 and Fig. 3, where the F1 score is 0.65 and AUC is 0.80. Compared to the prediction results in 2014, the prediction in 2015 maintains an equivalent performance, which is an indication of model ...