The code is different with paper in Embedding propagation

[Bulingbuling-ozgaga]

in paper[2.1-Embedding Propagation] said need to use σ2=var(dij2) to compute adjacency, but in the code[embedding-propagation.py--get_similarity_matrix()], which use function-torch.std() to compute adjacency, but var is Variance, std is Standard Deviation

[prlz77]

Thanks for letting us know! We will update the arxiv to correct this typo.