Active Multi-task Learning via Bandits
By Meng Fang, Dacheng Tao. 2015
37 citations recorded by the source corpus.
In multi-task learning, the multiple related tasks allow each one to benefit from the learning of the others, and labeling instances for one task can also affect the other tasks especially when the task has a small number of labeled data. Thus labeling effective instances across different learning tasks is important for improving the generalization error of all tasks. In this paper, we propose a new active multi-task learning paradigm, which selectively samples effective instances for multi-task learning. Inspired by the multi-armed bandits, which can balance the trade-off between the exploitation and exploration, we introduce a new active learning strategy and cast the selection procedure as a bandit framework. We consider both the risk of multi-task learner and the corresponding confidence bounds and our selection tries to balance this trade-off. Our proposed method is a sequential algorithm, which at each round maintains a sampling distribution on the pool of data, queries the label for an instance according to this distribution and updates the distribution based on the newly trained multi-task learner. We provide an implementation of our algorithm based on a popular multi-task learning algorithm that is trace-norm regularization method. Theoretical guarantees are developed by exploiting the Rademacher complexities. Comprehensive experiments show the effectiveness and efficiency of the proposed approach.
Subfields: Artificial Intelligence, Management Science and Operations Research
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Qiang Yang
- Yu Zhang
- Mingsheng Long
- Jianmin Wang
- Dongrui Wu
- Sinno Jialin Pan
- Sebastian Ruder
- Philip S. Yu
In Management Science and Operations Research
Citations in the corpus
- An Overview of Multi-task Learning (2018, neutral): “Moreover, a selection strategy, a tradeoffbetweenthelearningriskofalow-rankMTL modelbasedonthetrace-normregularizationanda confidenceboundsimilartomulti-armedbandits,is proposedin[68].”
- A Survey on Multi-Task Learning (2017, background): “Inspired by multi-armed bandits which balance the trade-off between the exploitation and exploration, a selection strategy is proposed in [122] to consider both the risk of multi-task learner based on the trace norm regularization and the corresponding confidence bound.”