“…Similar to the data sampling in Section 3.2, we can assign a task sampling weight đť‘ź 𝑡 for task 𝑡, which is also called mixing ratio, to control the frequency of data batches from task 𝑡. The most common task scheduling technique is to shuffle between different tasks [5,20,30,33,38,44,51,71,73,79,80,89,93,99,102,108,109,114,118], either randomly or according to a pre-defined schedule. While random shuffling is widely adopted, introducing more heuristics into scheduling could help further improving the performance of MTL models.…”