Self-Paced Multitask Learning with Shared Knowledge
This addresses the challenge of optimizing task selection in multitask learning for machine learning practitioners, though it appears incremental as it builds on existing multitask formulations.
The paper tackles the problem of improving multitask learning by introducing self-paced task selection, which sequentially chooses easier-to-harder tasks based on shared knowledge, and results show it outperforms baseline methods in all experiments.
This paper introduces self-paced task selection to multitask learning, where instances from more closely related tasks are selected in a progression of easier-to-harder tasks, to emulate an effective human education strategy, but applied to multitask machine learning. We develop the mathematical foundation for the approach based on iterative selection of the most appropriate task, learning the task parameters, and updating the shared knowledge, optimizing a new bi-convex loss function. This proposed method applies quite generally, including to multitask feature learning, multitask learning with alternating structure optimization, etc. Results show that in each of the above formulations self-paced (easier-to-harder) task selection outperforms the baseline version of these methods in all the experiments.