Multitask learning aims at solving a set of related tasks simultaneously, by exploiting the shared knowledge for improving the performance on individual tasks. Hence, an important aspect of multitask learning is to understand the similarities within a set of tasks. Previous works have incorporated this similarity information explicitly (e.g., weighted loss for each task) or implicitly (e.g., adversarial loss for feature adaptation), for achieving good empirical performances. However, the theoretical motivations for adding task similarity knowledge are often missing or incomplete. In this paper, we give a different perspective from a theoretical point of view to understand this practice. We first provide an upper bound on the generalization error of multitask learning, showing the benefit of explicit and implicit task similarity knowledge. We systematically derive the bounds based on two distinct task similarity metrics: H divergence and Wasserstein distance. From these theoretical results, we revisit the Adversarial Multi-task Neural Network, proposing a new training algorithm to learn the task relation coefficients and neural network parameters iteratively. We assess our new algorithm empirically on several benchmarks, showing not only that we find interesting and robust task relations, but that the proposed approach outperforms the baselines, reaffirming the benefits of theoretical insight in algorithm design.
Gap Minimization for Knowledge Sharing and Transfer
University of Western Ontario(西安大略大学);Massachusetts Institute of Technology(麻省理工学院);Université Laval(拉瓦尔大学);Beihang University(北京航空航天大学);McGill University(麦吉尔大学);University of Pennsylvania(宾夕法尼亚大学)
Clustering Markov Decision Processes For Continual Transfer
University of Edinburgh(爱丁堡大学);Blue Yonder UK Ltd.(英国Blue Yonder有限公司);Council for Scientific and Industrial Research(科学与工业研究理事会);University of the Witwatersrand(威特沃特斯兰德大学)