Interpretable MTL from Heterogeneous Domains using Boosted Tree
This addresses interpretability and domain heterogeneity in industrial multi-task learning, but it is incremental as it builds on existing boosted tree methods.
The paper tackles the problem of multi-task learning with heterogeneous domains and interpretability demands by proposing a two-stage boosted tree method, achieving validated effectiveness on benchmark and real-world datasets.
Multi-task learning (MTL) aims at improving the generalization performance of several related tasks by leveraging useful information contained in them. However, in industrial scenarios, interpretability is always demanded, and the data of different tasks may be in heterogeneous domains, making the existing methods unsuitable or unsatisfactory. In this paper, following the philosophy of boosted tree, we proposed a two-stage method. In stage one, a common model is built to learn the commonalities using the common features of all instances. Different from the training of conventional boosted tree model, we proposed a regularization strategy and an early-stopping mechanism to optimize the multi-task learning process. In stage two, started by fitting the residual error of the common model, a specific model is constructed with the task-specific instances to further boost the performance. Experiments on both benchmark and real-world datasets validate the effectiveness of the proposed method. What's more, interpretability can be naturally obtained from the tree based method, satisfying the industrial needs.