I am asking this question from context of transfer learning paradigm of machine learning.

In transfer learning, we are given different domains one of which is a target domain and others, the auxiliary domains. Now in order to complete a task in the target domain, we adapt the auxiliary domains so that it suits our target domain task.

Is this same as exploiting multiple auxiliary domains to effect our target domain task by making use of complementary information present in these auxiliary domains ?

I have seen literature dealing with domain adaptation and with using complementary information present in different domains (coming from different sources). Are these fundamentally the same ?


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.