Code Problem

Question

Code Problem

qiushuigongchang opened this issue 2 years ago · 8 comments

hi, i saw the ‘finetune_t’ parameter in model.py (self.log_inv_t = torch.nn.Parameter(torch.tensor(1.0 / args.t).log(), requires_grad=args.finetune_t), in line 31), but i only find 'finetune-t' this parameter, Are the two parameters the same?

Answer 1 · 2022-10-23T12:17:53.000Z

Yes, they are the same.

Answer 2 · 2022-10-23T12:22:54.000Z

Thanks a lot！

Answer 3 · 2022-10-29T07:54:18.000Z

hi, I'm a little confused , What does the triplet_mask do in models.py(in line 96)

Answer 4 · 2022-10-29T12:54:43.000Z

It is used to mask out false negatives during training.

For example, given two triples in a batch (obama, instance of, politician), (biden, is, US president), default in batch negatives will treat (obama, instance of, politician) as a positive and (obama, instance of, US president) as a negative. But the latter one is in fact a correct triple. So we need to mask it out for loss computation.

Answer 5 · 2022-10-29T13:52:52.000Z

Closed-world assumption (CWA) and Open-world assumption (OWA) , is it?

Answer 6 · 2022-10-31T08:45:18.000Z

hi, I'm a little confused , i understand head + relation -> tail when calculating the loss function, but what mean tail -> head + relation in trainer.py(in line 161), your help was very much appreciated.

Answer 7 · 2022-10-31T09:02:56.000Z

This is simply computing contrastive loss from two directions.

head + relation -> tail says: given a head entity and relation, which tail entity is correct?

tail -> head + relation says: given a tail entity, which head entity + relation is correct?

You can refer to A Simple Framework for Contrastive Learning of Visual Representations for perhaps easier understanding.

Answer 8 · 2022-10-31T14:52:10.000Z

thank you for helping me