@tkipf

When I displayed the graph I got a graph with many components. Is this correct? pdf attached. Maybe you included extra info in the edge list?

cora.pdf

Hi, When I run train.py there is a error message says: Loading cora dataset... Traceback (most recent call last): File "train.py", line 104, in train(epoch) File "train.py", line 69, in train output = model(features, adj) File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 206, in call result = self.forward(*input, **kwargs) File "build/bdist.linux-x86_64/egg/pygcn/models.py", line 15, in forward x = F.relu(self.gc1(x, adj)) File "/usr/local/lib/python2.7/dist-packages/torch/nn/modules/module.py", line 206, in call result = self.forward(*input, **kwargs) File "build/bdist.linux-x86_64/egg/pygcn/layers.py", line 61, in forward return output + self.bias File "/usr/local/lib/python2.7/dist-packages/torch/autograd/variable.py", line 745, in add return self.add(other) File "/usr/local/lib/python2.7/dist-packages/torch/autograd/variable.py", line 283, in add return self._add(other, False) File "/usr/local/lib/python2.7/dist-packages/torch/autograd/variable.py", line 277, in _add return Add(inplace)(self, other) File "/usr/local/lib/python2.7/dist-packages/torch/autograd/_functions/basic_ops.py", line 20, in forward return a.add(b) RuntimeError: inconsistent tensor size at /b/wheel/pytorch-src/torch/lib/TH/generic/THTensorMath.c:831

I saw you assign train/val/test follow this way: idx_train = range(140) idx_val = range(200, 500) idx_test = range(500, 1500)

I don't understand why you assign test sample number much more than train and val?

I have multiple graphs for node classification task. All the examples I've seen so far was for graph classification(or there is just one graph for node classification task). Although I've seen building block diagonal adjacency matrix, I'm not sure if it is for graph classification or node. Also I didn't understand whether should I create a block diagonal matrix with feature matrix and labels or not.

Let's suppose I have 20 different graphs(with different number of nodes, edges, features). And each node of every graph is labeled. All the nodes in first 10 graphs are for training, all the nodes of the next 5 graphs are for val, and all the nodes of last 5 graphs are for test, and what I try to do is predicting labels of the nodes for the graphs in test-set. How can I input multiple graphs into GCN with these conditions for node classification task(not for graph classification).? If the solution is diagonal adj. matrix, should I do the same for labels and feature matrix?

Hi @tkipf, thank you so much for providing the code.

I'm wondering if it's possible to scale this implementation up to millions of nodes (obviously the number of edges must scale linearly), for example a grid. I'm not familiar with PyTorch's sparse matrix implementation, so I'm not sure if representing the adjacency matrix as a sparse matrix is enough to deal with large graphs?

Hi tkipf, thank you for your amazing work! in utils.py, starts from Line 36,

    # build symmetric adjacency matrix
    adj = adj + adj.T.multiply(adj.T > adj) - adj.multiply(adj.T > adj)

As far as I understand, these lines are turning a directed adjacency matrix into an undirected adjacency matrix? Since adj is a 0-1 matrix, then for the positions adj[i,j] where adj.T > adj, we should have adj[i,j] = 0, so the - adj.multiply(adj.T > adj) part is always zero.

Then what's the purpose of having that part, or am I understand it incorrectly?

` adj = sp.coo_matrix((np.ones(edges.shape[0]), (edges[:, 0], edges[:, 1])), shape=(labels.shape[0], labels.shape[0]), dtype=np.float32)

# build symmetric adjacency matrix
adj = adj + adj.T.multiply(adj.T > adj) - adj.multiply(adj.T > adj)`

I don't understand how the last line code produces the symmetric matrix. And I think it is intuitive to build the symmetric like this adj = adj + adj.T

Can anyone help to answer my questions? thanks a lot

Hi Kipf,

Nice work. I am trying to run the model but failed to get the same result everytime even with the below lines.

np.random.seed(args.seed) torch.manual_seed(args.seed) if args.cuda: torch.cuda.manual_seed(args.seed)

Hello, thank you for your great work.

I want to extend gcn which involves message passing, but I'm new to GCN so I have a minor question.

I have to types of node A, B. Basically I want to train different weights jointly. (Weight_AA, Weight_AB, Weight_BA, Weight_BB) During the node representation update, A(t+1) = Weight_AA*A(t)adj(AA) + Weight_ABB(t)adj(BA) B(t+1) = Weight_BBB(t)adj(BB) + Weight_BAA(t)*adj(AB) The first terms are simple graph convolution layer with adj(AA), adj(BB) are both square but for the adj(BA), adj(AB) it might not be square, (# of two types of nodes will differ)

Can I use non-square adj matrix during the whole process? (normalize, forward, ...)

Hi @tkipf, thanks for your awesome work and providing this code!

I have a bit of a novice question: I'm trying to process my graph's features through a GCN in mini-batches. I.e. let's say I have a 1000-node graph and I want to process it through the GCN in mini-batches of size 50.

It doesn't seem like the code currently supports this because we have to multiply by the full adjacency matrix in the GCN layer's forward pass - do you have any sense of how I can support these "batch" operations? Better yet, do you have example code that does this?

My code looks something like:

z0 = F.tanh(self.gcn1(x, self.fancy_adj))

where x is a sampled batch of size 50 x F (not the full batch of 1000 x F) and self.fancy_adj is the adjacency matrix transformed as suggested in your paper ( adjacency + identity + row normalized). The problem, of course, is that self.fancy_adj is a 1000 x 1000 matrix. Even if I take just the rows of self.fancy_adj corresponding to the 50 points in the batch, then the adjacency matrix becomes a 50 x 1000 matrix which can't be multiplied by the 50 x F sampled batch.

When I read the papers, I saw a lot of formulas on how to calculate the adjacency matrix. We need matrix D and A in the formula as well. But when I read the code in this project, I found that you calculate the adj matrix without D. And I also don't understand how you calculate the adj. Could you explain it in the simple way? Thanks very much.

Hi,tkipf. when I use pygcn deal with citeseer dataset, there is a abnormal issue：dtype=np.int32).reshape(edges_unordered.shape)，TypeError: int() argument must be a string, a bytes-like object or a number, not 'NoneType'. How I dealing with it? Looking forward to your reply，Thank you!

I see the code in utils.py idx_train = range(140) idx_val = range(200, 500) idx_test = range(500, 1500)

I cannot understand it, because the ratio of they may be 6:2:2 if the dataset is smaller.

Anyone can help me?

When we normalized features, it seemed that the columns were features and the rows were samples, so why not normalize the columns?

Could someone give me some suggestions?

other scope dataset is a file (one file) and shape is below column1, column2, column3, ...column9, label 1500, 45, 1, .... 0 933, 22, 0, .... 0 1234, 30, 1, .... 1 1112, 23, 0, .... 0 ...

Let me know how to transform to above dataset with this code

I try below command

log-> python setup.py install

running install error: can't create or remove files in install directory

The following error occurred while trying to add or remove files in the installation directory:

[Errno 13] Permission denied: '/usr/local/lib/python3.7/dist-packages/test-easy-install-1558.write-test

...

and try below command $ sudo python setup.py install log -> ... Best match: scipy 1.7.0 Processing scipy-1.7.0.tar.gz Writing /tmp/easy_install-v4yo41y1/scipy-1.7.0/setup.cfg Running scipy-1.7.0/setup.py -q bdist_egg --dist-dir /tmp/easy_install-v4yo41y1/scipy-1.7.0/egg-dist-tmp-d7yw9bg_ /tmp/easy_install-v4yo41y1/scipy-1.7.0/setup.py:492: UserWarning: Unrecognized setuptools command ('-q bdist_egg --dist-dir /tmp/easy_install-v4yo41y1/scipy-1.7.0/egg-dist-tmp-d7yw9bg_'), proceeding with generating Cython sources and expanding templates ' '.join(sys.argv[1:]))) Error: 'pybind11' must be installed before running the build.

please help me!!

Hi, I'm learning GCN and read your code, Not sure whats the use of fast mode? Seems that dropout may make the eval set accuracy inaccurate? I'm a learner so probably just me not knowing enough.