graphlearn_torch/python/distributed/dist_neighbor_sampler.py [451:468]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        dst_neg = neg_pair[1]
        dst = torch.cat([dst, dst_neg], dim=0)
        assert edge_label is None
    # Neighbor Sampling
    if input_type is not None: # hetero
      if input_type[0] != input_type[-1]:  # Two distinct node types:
        src_seed, dst_seed = src, dst
        src, inverse_src = src.unique(return_inverse=True)
        dst, inverse_dst = dst.unique(return_inverse=True)
        seed_dict = {input_type[0]: src, input_type[-1]: dst}
      else:  # Only a single node type: Merge both source and destination.
        seed = torch.cat([src, dst], dim=0)
        seed, inverse_seed = seed.unique(return_inverse=True)
        seed_dict = {input_type[0]: seed}

      temp_out = []
      for it, node in seed_dict.items():
        seeds = NodeSamplerInput(node=node, input_type=it)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



graphlearn_torch/python/sampler/neighbor_sampler.py [370:387]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        dst_neg = neg_pair[1]
        dst = torch.cat([dst, dst_neg], dim=0)
        assert edge_label is None
    # Neighbor Sampling
    if input_type is not None: # hetero
      if input_type[0] != input_type[-1]:  # Two distinct node types:
        src_seed, dst_seed = src, dst
        src, inverse_src = src.unique(return_inverse=True)
        dst, inverse_dst = dst.unique(return_inverse=True)
        seed_dict = {input_type[0]: src, input_type[-1]: dst}
      else:  # Only a single node type: Merge both source and destination.
        seed = torch.cat([src, dst], dim=0)
        seed, inverse_seed = seed.unique(return_inverse=True)
        seed_dict = {input_type[0]: seed}

      temp_out = []
      for it, node in seed_dict.items():
        seeds = NodeSamplerInput(node=node, input_type=it)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -