Efficiently Identifying Task Groupings for Multi-Task Learning
This addresses the challenge of designing efficient multi-task learning models for computer vision, though it is incremental as it builds on existing task grouping methods.
The paper tackles the problem of efficiently selecting which tasks should train together in multi-task learning to avoid performance degradation, proposing a method that determines task groupings in a single run by analyzing gradient effects. On the Taskonomy dataset, this method reduces test loss by 10.0% compared to training all tasks together and operates 11.6 times faster than a state-of-the-art task grouping method.
Multi-task learning can leverage information learned by one task to benefit the training of other tasks. Despite this capacity, naively training all tasks together in one model often degrades performance, and exhaustively searching through combinations of task groupings can be prohibitively expensive. As a result, efficiently identifying the tasks that would benefit from training together remains a challenging design question without a clear solution. In this paper, we suggest an approach to select which tasks should train together in multi-task learning models. Our method determines task groupings in a single run by training all tasks together and quantifying the effect to which one task's gradient would affect another task's loss. On the large-scale Taskonomy computer vision dataset, we find this method can decrease test loss by 10.0% compared to simply training all tasks together while operating 11.6 times faster than a state-of-the-art task grouping method.