Yes, approximately. If you can do it for only e.g. transformers, but not other things, that would be interesting.
I guess a closer analogy would be “What if the family of strategies only works for transformer-based GANs?” than “What if the family of strategies only works for transformers?”. As in there’d be heavy restrictions on both the “layer types”, the I/O, and the training procedure?
Yes, approximately. Thinking about how to get one question right might be a productive way to do research. However, if you have a strategy for answering 1 question right, it should also work for other questions.
What if each question/family of questions you want to answer requires careful work on the structure of the model? So the strategy does generalize, but it doesn’t generalize “for free”?
I guess a closer analogy would be “What if the family of strategies only works for transformer-based GANs?” than “What if the family of strategies only works for transformers?”. As in there’d be heavy restrictions on both the “layer types”, the I/O, and the training procedure?
What if each question/family of questions you want to answer requires careful work on the structure of the model? So the strategy does generalize, but it doesn’t generalize “for free”?