A Survey on Multi-Task Learning

Multi-Task Learning (MTL) is a learning paradigm in machine and its aim to leverage useful information contained multiple related tasks help improve the generalization performance of all tasks. In this paper, we give survey for MTL from perspective algorithmic modeling, applications theoretical analyses. For definition then classify different algorithms into five categories, including feature approach, low-rank task clustering relation approach decomposition as well discussing characteristics each approach. order further, can be combined with other paradigms semi-supervised learning, active unsupervised reinforcement multi-view graphical models. When number large or data dimensionality high, review online, parallel distributed models reduction hashing reveal their computational storage advantages. Many real-world use boost representative works paper. Finally, present analyses discuss several future directions MTL.