KGNN-LS
KGNN-LS copied to clipboard
hwwang55
A tensorflow implementation of Knowledge-aware Graph Neural Networks with Label Smoothness regularization
I was wondering if there is a way to add user & item features? For e.g user features could be weight, height, age, etc.
Hello, I found a performance issue in the definition of `_build_label_smoothness_loss`, src/model.py, [`tf.expand_dims`](https://github.com/hwwang55/KGNN-LS/blob/3afd76361b623e9e38b822861c79bcd61dae41aa/src/model.py#L114) will be created repeatedly during program execution, resulting in reduced efficiency. I think it should be created...
When I run the main.py file I got an error AttributeError: module 'tensorflow' has no attribute 'contrib' I am updating the error. Please help how to resolve it or how...
I am using yolo model for object detection but got a error no defined YOLO.
Dear Dr. Wang, Could you provide the actual semantic meanings of relations in dataset Restaurant? Otherwise, it is impossible to conduct experiments on this dataset with meta-path based methods. I...
I want to know how knowledge graph file (kg.txt) is generated? There is no code to let me see and understand how to achieve it. thank you!
It requires to modify python main code to select recommendation subject(movie, book, music, restaurant). If we can give a parameter for the subject without code modification, then it will be...
Hi, Your code is very clear. But I have a question for the construction of the adjacency matrix. Because you split the data set into train, eval, and test set,...
Hello Mr. Wang I'm trying to reproduce your model on a new dataset that uses jurisprudemce documents. My only question is how was the item_index2entity_id.txt dataset generated? Are the item...
