Open zhanglei1172 opened 1 year ago
Hi, thanks for your question. The approximation of Shapley value is conducted across different inputs. We found that the same operation may show very large contribution on some of the input samples while having large negative value on others. So we evaluate the actual importance by mean minus std to mitigate the effect of input distribution.
Hi ! Thanks for your open source, but I'm a little confused about your code. https://github.com/Euphoria16/Shapley-NAS/blob/06497276e819a38af997415a5015900aa3e93667/train_search.py#L252
Why
minus
the std of samples? If it's a Monte Carlo approximation, just only need to calculate the sample mean.