论文标题
使用双重编程进行可解释的多任务学习
Towards Interpretable Multi-Task Learning Using Bilevel Programming
论文作者
论文摘要
可解释的多任务学习可以表示为基于学习模型的预测性能学习任务关系的稀疏图。由于许多自然现象表现出稀疏结构，因此对学习模型的稀疏性揭示了潜在的任务关系。此外，从完全连接的图形中的不同稀疏度揭示了各种类型的结构，例如集团，树，线，群集或完全断开的图。在本文中，我们提出了一种多任务学习的双重表述，从而引起稀疏图，从而揭示了基本的任务关系，以及一种有效的计算方法。我们从经验上展示了诱导的稀疏图如何改善学习模型的解释性及其在合成和真实数据上的关系，而无需牺牲概括性能。 https://bit.ly/graphguidedmtl上的代码
Interpretable Multi-Task Learning can be expressed as learning a sparse graph of the task relationship based on the prediction performance of the learned models. Since many natural phenomenon exhibit sparse structures, enforcing sparsity on learned models reveals the underlying task relationship. Moreover, different sparsification degrees from a fully connected graph uncover various types of structures, like cliques, trees, lines, clusters or fully disconnected graphs. In this paper, we propose a bilevel formulation of multi-task learning that induces sparse graphs, thus, revealing the underlying task relationships, and an efficient method for its computation. We show empirically how the induced sparse graph improves the interpretability of the learned models and their relationship on synthetic and real data, without sacrificing generalization performance. Code at https://bit.ly/GraphGuidedMTL
