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

Abstract

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.

References in corpus (11)

• Neural Architecture Search with Reinforcement Learning
• Learning Transferable Features with Deep Adaptation Networks
• Deep Domain Confusion: Maximizing for Domain Invariance
• Tent: Fully Test-time Adaptation by Entropy Minimization
• Central Moment Discrepancy (CMD) for Domain-Invariant Representation Learning
• Deep Multi-task Representation Learning: A Tensor Factorisation Approach
• Learning to Branch for Multi-Task Learning
• Modular Networks: Learning to Decompose Neural Computation
• Feature Partitioning for Efficient Multi-Task Architectures
• Flexible Multi-task Networks by Learning Parameter Allocation
• Recurrent Feedback Improves Feedforward Representations in Deep Neural Networks