What is the difference between multi-task learning and MultiModel learning?

Question

I would like to ask whether there are any differences between multi-task and multi-model learning?

Many Thanks

Answer 1

I think you mean Multimodal learning which deals with different kinds of data e.g. text, image, audio..etc and tries to learn a joint representation of the data.
Multitask learning aims to learn multiple tasks at the same time. Those tasks could be for data of the same kind e.g. translation, question answering, summarization..etc

You can have a look at the paper "One Model To Learn Them All" which deals with Multimodal and Multitask learning at the same time, so it might help you better understand the difference.