Timeline for How to know how correlated tasks are in Multitask learning?
Current License: CC BY-SA 4.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jan 26, 2022 at 19:38 | history | edited | Pedram | CC BY-SA 4.0 |
deleted 41 characters in body
|
| Feb 13, 2020 at 22:45 | history | edited | Pedram | CC BY-SA 4.0 |
added 80 characters in body
|
| Feb 13, 2020 at 22:45 | comment | added | Pedram | @Aksakal I did not come up with the "task correlation" this is what I saw in the original MTL paper (I just added the citation for the paper to the question.) and trying to understand what it means or how it can be measured. | |
| Feb 13, 2020 at 22:35 | comment | added | Aksakal | You came up with task correlation concept, so you must define it. In a degenerated case, imagine that you divided the dataset into two subsets. then you run them as if they were different tasks in MTL setup. would this be better than running the subsets separately? you bet it should, if nothing else, then at least because the sample size increased. would you call these tasks correlated? I don't know, because you didnt explain what you mean by correlation | |
| Feb 13, 2020 at 22:14 | comment | added | Pedram | @Aksakal in my case, tasks are NLP tasks. For example, a binary text classification task and a token-level task like Named Entity Recognition (just as an example here.) Back to your question, I'm exactly trying to figure out what "task correlation" means. You say they should share some features, what features are we talking about here? | |
| Feb 13, 2020 at 21:06 | comment | added | Aksakal | Can you explain what do you mean by task correlation? Tasks should share some features, they must be similar in some way, otherwise MTL will not make a sense | |
| Feb 13, 2020 at 17:49 | history | edited | Pedram |
edited tags
|
|
| Feb 13, 2020 at 5:52 | history | asked | Pedram | CC BY-SA 4.0 |