Hi, excellent work!
In equation 8 and 10 of the paper, you proposed a Bayes loss and a specific task classification parameter generation module. But I failed to find the implementation of them in the code, can you help me?
Thanks

Hi,
I see that the proposed model is optimized by minimizing the binary cross-entropy loss of query edges and Bayes by Backprop loss. But I failed to locate the calculation of Bayes loss L_B in the code.

Can you explain for me?
Thank you.

作者您好，我和朋友在运行这份代码的时候发现这样一个问题：
query的输入顺序是和support的顺序固定一致的，此时训练后的模型在验证集上准确率能有85.684%，比较高。然而在把query的顺序打乱的情况下训练模型，只能在验证集上得到77.042%的准确率。公认的是，query的顺序应该被打乱。我们认为是您的图神经网络出现了过拟合，学习到了query的固定顺序。您能对此作出解释吗？感谢。（上述准确率均是在一块2080ti GPU上训练得到的结果，由于显存的原因，我将train_batch_size和test_batch_size改小到了32和16）
Hello author, friends and I found this problem when running this code:
The input order of query is consistent with the order of support. At this time, the accuracy of the trained model on the validation set can be 85.684%, which is relatively high. However, when the query order is shuffled, the model can only obtain 77.042% accuracy on the validation set. It is generally accepted that the order of queries should be recognized. We think that your BGNN has overfitted and learned a fixed order of queries. Can you explain this? Thanks. (The above accuracy rates are obtained by training on a 2080ti GPU. Due to limited GPU memory, I changed the train_batch_size and test_batch_size to 32 and 16)