relational-gcn
relational-gcn copied to clipboard
tkipf
Keras-based implementation of Relational Graph Convolutional Networks
Hi, thanks for this interesting approach! I also read your paper and I still have an open question about the input features and the data set that you use. Am...
sorry run train.py and this is the error Traceback (most recent call last): File "/home/bfs/NEW_LAB/relational-gcn-master/rgcn/train.py", line 92, in W_regularizer=l2(L2))([X_in] + A_in) File "/home/bfs/miniconda3/envs/py27tf14_rgcn/lib/python2.7/site-packages/keras/engine/topology.py", line 548, in __call__ self.build(input_shapes) File "build/bdist.linux-x86_64/egg/rgcn/layers/graph.py",...
Can we apply the same relational GCN on the path queries dataset such as wordnet and freebass
hi , could you give the description of the format of the datasets? i want to know the how to design the format of my own datasets. thanks.
Hi, in the paper, there are 1,666,764 entities and 5,988,321 edges reported in the dataset of AM  However, in `rgcn/data/am`, there is only 1000 instances randomly sampled from the...
does r-gcn works on entity alignment (existing R-GCN seems only focus on classification and link prediction)? If yes, May I know do you have any working code on this?
I used model.save() but I got the error: Traceback (most recent call last): File "/Applications/PyCharm CE.app/Contents/plugins/python-ce/helpers/pydev/pydevd.py", line 1477, in _exec pydev_imports.execfile(file, globals, locals) # execute the script File "/Users/liang/Downloads/mee/3_rgcn/rgcn/train.py", line...
Hi @tkipf, first of all, thank you for your work on GCNs, I'm currently researching their application in my domain and really like the results so far. Sadly I'm stuck...
i changed X into X=sp.dia_matrix(A[0].shape) it was still errors. in fact, the version still bring many errors, e.g. return x=x.__dims, however, there doesn't exist the attribute "__dims"？
TypeError: Input layers to a `Model` must be `InputLayer` objects. Received inputs: [, , , , , , , , , , , , , , , , , ,...
