arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.10963cs.LGcs.CV
收藏

组合模型:模块化网络的多任务学习和知识转移

Compositional Models: Multi-Task Learning and Knowledge Transfer with Modular Networks

Google LLC(谷歌有限责任公司);Boston University(波士顿大学)

Andrey Zhmoginov, Dina Bashkirova, Mark Sandler

摘要:

条件计算和模块化网络最近被提出用于多任务学习和其他问题,作为将问题解决分解为多个可重用计算块的方法。我们提出了一种新的方法来学习模块化网络的基础上等距版本的ResNet与所有剩余块具有相同的配置和相同数量的参数。这种架构选择允许添加、移除和改变残差块的顺序。在我们的方法中,模块可以被反复调用,并允许通过调整计算顺序将知识转移到新的任务。这允许在任务之间进行软权重共享,而参数的数量只会有很小的增加。我们表明,我们的方法导致可解释的自组织模块的情况下,多任务学习,迁移学习和领域自适应,同时在这些任务上取得有竞争力的结果。从实践的角度来看,我们的方法允许:(a)通过调整计算顺序来重用现有模块以学习新任务,(b)将其用于无监督的多源领域自适应,以说明仅通过操纵预训练模块的顺序就可以实现对未见过数据的自适应,(c)显示我们的方法如何用于提高现有架构的准确性,用于图像分类任务,如ImageNet,不增加任何参数,通过多次重复使用相同的块。

英文摘要:

Conditional computation and modular networks have been recently proposed for multitask learning and other problems as a way to decompose problem solving into multiple reusable computational blocks. We propose a new approach for learning modular networks based on the isometric version of ResNet with all residual blocks having the same configuration and the same number of parameters. This architectural choice allows adding, removing and changing the order of residual blocks. In our method, the modules can be invoked repeatedly and allow knowledge transfer to novel tasks by adjusting the order of computation. This allows soft weight sharing between tasks with only a small increase in the number of parameters. We show that our method leads to interpretable self-organization of modules in case of multi-task learning, transfer learning and domain adaptation while achieving competitive results on those tasks. From practical perspective, our approach allows to: (a) reuse existing modules for learning new task by adjusting the computation order, (b) use it for unsupervised multi-source domain adaptation to illustrate that adaptation to unseen data can be achieved by only manipulating the order of pretrained modules, (c) show how our approach can be used to increase accuracy of existing architectures for image classification tasks such as ImageNet, without any parameter increase, by reusing the same block multiple times.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑