Multi-Task Learning with Labeled and Unlabeled Tasks
This work addresses a practical challenge in multi-task learning for scenarios with limited labeled data, though it appears incremental as it builds on existing instance-based transfer methods.
The paper tackles the problem of multi-task learning where only some tasks have labeled data, introducing a setting where information must be transferred between labeled and unlabeled tasks. It presents an algorithm with generalization bounds and demonstrates effectiveness through experiments on synthetic and real data.
In multi-task learning, a learner is given a collection of prediction tasks and needs to solve all of them. In contrast to previous work, which required that annotated training data is available for all tasks, we consider a new setting, in which for some tasks, potentially most of them, only unlabeled training data is provided. Consequently, to solve all tasks, information must be transferred between tasks with labels and tasks without labels. Focusing on an instance-based transfer method we analyze two variants of this setting: when the set of labeled tasks is fixed, and when it can be actively selected by the learner. We state and prove a generalization bound that covers both scenarios and derive from it an algorithm for making the choice of labeled tasks (in the active case) and for transferring information between the tasks in a principled way. We also illustrate the effectiveness of the algorithm by experiments on synthetic and real data.