HGN

HGN copied to clipboard

Would the parameters work if the output dimension of training and prediction are different ?

1

 In the code(gating_network.py) above the output dimensions are different for training(batch_size,(target_length+neg_length)) and test(batch_size, num_item). So my question is whether the parameters still work for test ? Is this a...

superjdz

A mistake on negative sampling

1

https://github.com/allenjack/HGN/blob/8bf6008e106fc3b1bc882bab6e65698e62c54ac6/run.py#L91 I think you may change it to this one. Otherwise, positive items can be sampled. ``` ret = np.asarray(neg_samples).reshape(train_matrix.shape[0], num_sets, num_neg) # [n_user, ] return np.transpose(ret, axes=[1, 0, 2])```

BenjaminChoou