Conflict-Averse Gradient Descent for Multi-task Learning

arXiv:2110.14048v2 Announce Type: replace
Abstract: The goal of multi-task learning is to enable more efficient learning than single task learning by sharing model structures for a diverse set of tasks. A standard multi-task learning objective is to minimize the average loss across all tasks. While straightforward, using this objective often results in much worse final performance for each task than learning them independently. A major challenge in optimizing a multi-task model is the conflicting gradients, where gradients of different task …

abstract arxiv conflict cs.ai cs.lg diverse gradient loss multi-task learning set standard tasks type