when running HCHA experiment getting next error:

 self.__set_size__(size, dim, data)
  File "/opt/anaconda3/envs/wave-pyg/lib/python3.9/site-packages/torch_geometric/nn/conv/message_passing.py", line 165, in __set_size__
    raise ValueError(
ValueError: Encountered tensor with size 4287 in dimension 0, but expected size 2708.

First of all thank you very much for your excellent work, I tried to run your program on my own computer. I am using the latest version 2.0.3 of pyg, and version 1.9.0 of pytorch.

As you know, there are some differences between the 2.0.3 version of pyg and the 1.6.3 version used in your project. After my own modification, I have been able to run HyperGCN, CEGAT, CEGCN and AllSetTransformer, but when I try to run HGNN, HNHN and HCHA, the code always reports an error, and the error occurs here：

layers.py line405 self.flow = 'target_to_source' out = self.propagate(hyperedge_index, x=out, norm=D, alpha=alpha, size=(num_edges, num_nodes))

or layers.py line303 self.flow = 'target_to_source' out = self.propagate(hyperedge_index, x=out, norm=data.D_v_alpha_inv, size=(num_edges, num_nodes)) and it shows : ValueError: Encountered tensor with size 4287 in dimension 0, but expected size 2708.

with 'cora' dataset.

I really find it very difficult to solve this problem, could you please update your code to help me out. Thank you very much

Model: AllSetTransformer If I understood correctly, in the original code implementation all the hyperedges are assumed to have unit weight. Now my hypergraph has weighted hyperedges, how do I integrate this information into the code?

I noticed the comment below https://github.com/jianhao2016/AllSet/blob/15cbc85a9c325815ab7b8f4bf51ff8e56bac2628/src/models.py#L330 . If the hyperedge weight can be considered as hyperedge feature, where do I concat the hyperedge weight exactly? Is it after the final output of the PMA of the self.V2EConvs block i.e. https://github.com/jianhao2016/AllSet/blob/15cbc85a9c325815ab7b8f4bf51ff8e56bac2628/src/layers.py#L157 ?

Hi AllSet authors,

In the appendix of the paper, I noticed that the feature dimensions of the House and Walmart dataset are fixed to 100, but I found that in the code, the feature dimensions are in [num_nodes, num_classes] of the "load_other_datasets.py" file.

I guess it is just a typo but still would like to double-check with you which dimension (100, or num_classes) was used for the reported results in the paper.

Thank you for making the three new datasets available to the community, the paper is really a solid work!

Hi,

I'm trying to understand what your code do. Let's say that we have a toy dataset like this: V;E = v0, v0, v1, v1, v2, v2, v3
e1, e2, e2, e1, e2, e3, e3

Which translate into this edge_index: [[0, 0, 1, 1, 2, 2, 3], [4, 5, 5, 4, 5, 6, 6]],

import numpy as np

edge_index = torch.tensor([[0, 0, 1, 1, 2, 2, 3], [4, 5, 5, 4, 5, 6, 6]], dtype=torch.long) edge_index = coalesce(edge_index)

ei = np.array(edge_index) num_nodes = len(np.unique(ei[0])) num_hyperedges = len(np.unique(ei[1]))

data = Data(edge_index=edge_index, n_x = num_nodes, num_hyperedges=num_hyperedges)

Now, if I use your Add_Self_Loops code I obtain this edge_index: tensor([[ 0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3]
[ 4, 5, 7, 4, 5, 8, 5, 6, 9, 6, 10]])

Which is a little bit confusing. Shoudn't be added the same node? What are you doing in this code exactly, and why?

Same question for expand_edge_index.

tensor([[ 0, 0, 0, 1, 1, 1, 2, 2, 2, 3, 3]
[ 5, 7, 8, 4, 6, 8, 6, 7, 10, 9, 11]])

What kind of expansion are you implementing? What is the difference between the two implementations? Why are they needed for your models AllDeepSets and AllSetTransformer?

Hi, this is a nice work. I read the code: https://github.com/jianhao2016/AllSet/blob/0d0e399a9168829fa898dd56f3d32bee36953b04/src/train.py#L325-L327 https://github.com/jianhao2016/AllSet/blob/0d0e399a9168829fa898dd56f3d32bee36953b04/src/train.py#L345 https://github.com/jianhao2016/AllSet/blob/0d0e399a9168829fa898dd56f3d32bee36953b04/src/train.py#L478 It seems that you train the model with all the data in a batch. Thus I have a question about how to set batch size when I train the AllSet model. Thank you.