can I adapt the code to multi-label classificaiton? about pygcn HOT 12 OPEN

thanks.

I changed the the GCN model return F.sigmoid(x)
and replace the loss function F.nll_loss using loss_train = F.binary_cross_entropy(output[idx_train], labels[idx_train]). is my change correct?

from pygcn.

from pygcn.

from pygcn.

hello, have you finish the multi-label problem?

from pygcn.

I need to use GCN with TensorFlow, have you try multi-label problem with Tensorflow?
The changes I make as follow:
loss = tf.nn.sigmoid_cross_entropy_with_logits(logits=preds, labels=labels) (from metrics.py)
correct_prediction = tf.equal(preds, labels). (from metrics.py)
return tf.nn.sigmoid(self.outputs). (from models.py)

So is it correct?

from pygcn.

@Chengmeng94 It seems to be correct. Make sure to adapt the accuracy function as well to handle a sigmoid output instead of a softmax output. currently it is just taking the max, as you would expect for a softmax function, so it is just evaluating a single label. This is typically done with some threshold.

from pygcn.

@anjanaskumar27 My response was to a mult-label situation, rather than a multi-class situation. I think the original code already works for multi-class situations.

from pygcn.

@Baukebrenninkmeijer sorry, my bad. I meant to ask procedure for multi label. The following are my changes:
loss = tf.nn.sigmoid_cross_entropy_with_logits(logits=preds, labels=labels) and correct_prediction = tf.equal(preds, labels) in metrics.py .
And use tf.nn.sigmoid(self.outputs) to predict in models.py.
As suggested in tkipf/gcn#119
Can you tell me what is wrong here? Or what needs to be updated in accuracy?

from pygcn.

@anjanaskumar27 As far as I can see here, this should be correct except maybe for the metric. I'm not an expert on metrics for multilabel, but I expect just accuracy (which is what you get with the tf.equal) is not the most appropriate, although it still gives you some indication.

from pygcn.

@Chengmeng94 @tkipf @Baukebrenninkmeijer , to allow multi-label mulit-class classification:

In addition to @Chengmeng94 changes (as follows),
loss = tf.nn.sigmoid_cross_entropy_with_logits(logits=preds, labels=labels) in model.py
tf.nn.sigmoid(self.outputs) to predict in models.py

I added,
logits_prob = tf.nn.sigmoid(preds, name = 'log_prob')
predictions = tf.cast(logits_prob > 0.5, tf.float32,name='predictions')
correct_prediction = tf.equal(predictions,labels)

Is this correct?

from pygcn.

@anjanaskumar27 tensorflow is not my strongsuit, but a quick google advised the following. Use tf.round() to push the prediction to either 0 or 1. Then you can calculate metrics. This appears to make sense. Let me know if it works out. Please report if correct_prediction is an NxL matrix, where N is the number of samples and L the number of labels.
So in short, i think you should do:

correct_prediction = tf.equal(tf.round(tf.nn.sigmoid(self.outputs)), labels)
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

from pygcn.

@Baukebrenninkmeijer , thank you for the suggestion. I am new to tensorflow as well, thus finding it little tricky to modify things.
For me, the size of correct predictions is 2x1. I may have to fix this?
Additionally, wrt to the code in utils.py, line #77, idx_val = range(len(y), len(y)+500), do you have any idea why they add 500 here? My graph with total nodes of 70, seems to fail because of this.
Thank you for the help!

from pygcn.