Experiment can not be reproduced

[minestoo]

The code and datasets are dramatically messy with poor readability and bad format, and this model can not be easily applied on other datasets. Moreover, even on the offered datasets, the code is not executed successfully (without any modification, just as what you provided).

Information:

Traceback (most recent call last):
  File "/tmp/SCD/main.py", line 145, in <module>
    train(args, construct_local_map(args))
  File "/tmp/SCD/main.py", line 65, in train
    predict(args, local_map, net, epoch)
  File "/tmp/SCD/main.py", line 84, in predict
    output = net.forward_test(input_stu_ids, input_exer_ids, input_knowledge_embs, input_nodes, output_nodes, blocks)
  File "/tmp/SCD/model.py", line 100, in forward_test
    node_emb2 = self.gnet2(blocks[1], node_emb1)
  File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)
  File "/tmp/SCD/gnn.py", line 55, in forward
    dstdata = self.mods[etype](rel_graph, (src_inputs[stype], dst_inputs[dtype]), *mod_args.get(etype, ()), **mod_kwargs.get(etype, {}))
  File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1110, in _call_impl
    return forward_call(*input, **kwargs)
  File "/root/miniconda3/lib/python3.8/site-packages/dgl/nn/pytorch/conv/gatconv.py", line 295, in forward
    graph.dstdata.update({'er': er})
  File "/root/miniconda3/lib/python3.8/_collections_abc.py", line 832, in update
    self[key] = other[key]
  File "/root/miniconda3/lib/python3.8/site-packages/dgl/view.py", line 81, in __setitem__
    self._graph._set_n_repr(self._ntid, self._nodes, {key : val})
  File "/root/miniconda3/lib/python3.8/site-packages/dgl/heterograph.py", line 4000, in _set_n_repr
    self._node_frames[ntid].update(data)
  File "/root/miniconda3/lib/python3.8/_collections_abc.py", line 832, in update
    self[key] = other[key]
  File "/root/miniconda3/lib/python3.8/site-packages/dgl/frame.py", line 405, in __setitem__
    self.update_column(name, data)
  File "/root/miniconda3/lib/python3.8/site-packages/dgl/frame.py", line 478, in update_column
    raise DGLError('Expected data to have %d rows, got %d.' %
dgl._ffi.base.DGLError: Expected data to have 225 rows, got 223.

[surqing]

Yes, I have the same question as you, is there a possibility that the author does not want us to reproduce his results. Don't force it.