Semisoft Task Clustering for Multi-Task Learning
This is an incremental improvement for multi-task learning researchers, addressing task clustering with mixed tasks.
The paper tackles the problem of multi-task learning by proposing a semisoft task clustering approach that reveals cluster structures for pure and mixed tasks while selecting relevant features, with experimental validation on synthetic and real-world datasets showing effectiveness and efficiency.
Multi-task learning (MTL) aims to improve the performance of multiple related prediction tasks by leveraging useful information from them. Due to their flexibility and ability to reduce unknown coefficients substantially, the task-clustering-based MTL approaches have attracted considerable attention. Motivated by the idea of semisoft clustering of data, we propose a semisoft task clustering approach, which can simultaneously reveal the task cluster structure for both pure and mixed tasks as well as select the relevant features. The main assumption behind our approach is that each cluster has some pure tasks, and each mixed task can be represented by a linear combination of pure tasks in different clusters. To solve the resulting non-convex constrained optimization problem, we design an efficient three-step algorithm. The experimental results based on synthetic and real-world datasets validate the effectiveness and efficiency of the proposed approach. Finally, we extend the proposed approach to a robust task clustering problem.