# Multi-Task Learning with Labeled and Unlabeled Tasks

arXiv: https://arxiv.org/abs/1602.06518 · HTML: https://mlsanity.com/paper/1602.06518/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Feb 2016.

## Built on by (most cited first, 17 of 17)

- [Semi-supervised Multi-task Learning for Semantics and Depth](https://mlsanity.com/paper/2110.07197/) (2021)
- [Scalarization for Multi-Task and Multi-Domain Learning at Scale](https://mlsanity.com/paper/2310.08910/) (2023)
- [Generative Modeling for Multi-task Visual Learning](https://mlsanity.com/paper/2106.13409/) (2021)
- [See Yourself in Others: Attending Multiple Tasks for Own Failure Detection](https://mlsanity.com/paper/2110.02549/) (2021)
- [How to distribute data across tasks for meta-learning?](https://mlsanity.com/paper/2103.08463/) (2021)
- [Best-Effort Adaptation](https://mlsanity.com/paper/2305.05816/) (2023)
- [Multitask Online Mirror Descent](https://mlsanity.com/paper/2106.02393/) (2021)
- [Multi-task Learning by Leveraging the Semantic Information](https://mlsanity.com/paper/2103.02546/) (2021)
- [From Low Intrinsic Dimensionality to Non-Vacuous Generalization Bounds in Deep Multi-Task Learning](https://mlsanity.com/paper/2501.19067/) (2025)
- [Disentangling Transfer and Interference in Multi-Domain Learning](https://mlsanity.com/paper/2107.05445/) (2021)
- [Fast Rate Bounds for Multi-Task and Meta-Learning with Different Sample Sizes](https://mlsanity.com/paper/2505.15496/) (2025)
- [AdaTask: Adaptive Multitask Online Learning](https://mlsanity.com/paper/2205.15802/) (2022)
- [Characterization of Transfer Using Multi-task Learning Curves](https://mlsanity.com/paper/2512.24866/) (2025)
- [Federated Learning with Unlabeled Clients: Personalization Can Happen in Low Dimensions](https://mlsanity.com/paper/2505.15579/) (2025)
- [BandiK: Efficient Multi-Task Decomposition Using a Multi-Bandit Framework](https://mlsanity.com/paper/2512.24708/) (2025)
- [Semi-overlapping Multi-bandit Best Arm Identification for Sequential Support Network Learning](https://mlsanity.com/paper/2512.24959/) (2025)
- [Joint Interference Detection and Identification via Adversarial Multi-task Learning](https://mlsanity.com/paper/2604.08607/) (2026)

## Abstract (arXiv)

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.