Saliency-Regularized Deep Multi-Task Learning
Saliency-Regularized Deep Multi-Task Learning
复制标题
DOI：
10.1145/3534678.3539442
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Guangji Bai;Liang Zhao
中科院分区：
文献类型：
--
作者：
Guangji Bai;Liang Zhao
多任务学习（MTL）是一个框架，它强制多个学习任务共享它们的知识，以提高它们的泛化能力。虽然浅层多任务学习可以学习任务关系，但它只能处理预定义的特征。现代深度多任务学习可以联合学习潜在特征和任务共享，但它们在任务关系上是模糊的。此外，它们预先定义了哪些层和神经元应该在任务之间共享，并且不能自适应学习。为了应对这些挑战，本文提出了一种新的多任务学习框架，通过补充现有的浅层和深层多任务学习场景的优势，联合学习潜在特征和显式任务关系。具体地说，我们提出了任务之间的输入梯度的相似性建模的任务关系，与它们的等价性的理论分析。此外，我们创新性地提出了一个多任务学习目标，明确学习任务关系的一个新的正则化。理论分析表明，由于所提出的正则化器的推广误差已减少。在多个多任务学习和图像分类基准上的大量实验表明，该方法的有效性，效率以及学习的任务关系模式的合理性。
Multi-task learning (MTL) is a framework that enforces multiple learning tasks to share their knowledge to improve their generalization abilities. While shallow multi-task learning can learn task relations, it can only handle pre-defined features. Modern deep multi-task learning can jointly learn latent features and task sharing, but they are obscure in task relation. Also, they pre-define which layers and neurons should share across tasks and cannot learn adaptively. To address these challenges, this paper proposes a new multi-task learning framework that jointly learns latent features and explicit task relations by complementing the strength of existing shallow and deep multitask learning scenarios. Specifically, we propose to model the task relation as the similarity between tasks' input gradients, with a theoretical analysis of their equivalency. In addition, we innovatively propose a multi-task learning objective that explicitly learns task relations by a new regularizer. Theoretical analysis shows that the generalizability error has been reduced thanks to the proposed regularizer. Extensive experiments on several multi-task learning and image classification benchmarks demonstrate the proposed method's effectiveness, efficiency as well as reasonableness in the learned task relation patterns.