GCN_AnomalyDetection

GCN_AnomalyDetection copied to clipboard

How to create train, test and validation set?

1

The model reports only the train loss and no validation loss is provided. Although the anomalies were added synthetically, therefore we know the ground truth and can use metrics of...

AmoghM

In the attributed network, how to convert the attribute information of the literal type into the vector of the numeric type? What do we need to do with the raw...

hahaymm

question

1

'pos_weight' and 'norm' are not defined in your VAE model,could you please give some suggestion?

LLLeyre

您好您的tensorflow代码中在进行数据集训练后，AUC指标在Amazon数据300次迭代大概为0.56；在Enron数据集为0.73（并且在大概60次迭代后，损失函数就没有发生变化了）；在Disney数据集中AUC指标为0.49，基于这些指标模型优势并未展现，不知道是不是我的操作有问题，请您指教，另外还有问题在'BlogCatalog', 'Flickr', 'ACM'数据集找不到gnd，也就是没有图中的标签。 Hello, in your TensorFlow code, after data set training, the AUC index for 300 iterations of Amazon data is approximately 0.56; The Enron dataset was 0.73 (and...

lihaonanleo