Regularize, Expand and Compress: Multi-task based Lifelong Learning via NonExpansive AutoML
arXiv:1903.08362
Abstract
Lifelong learning, the problem of continual learning where tasks arrive in sequence, has been lately attracting more attention in the computer vision community. The aim of lifelong learning is to develop a system that can learn new tasks while maintaining the performance on the previously learned tasks. However, there are two obstacles for lifelong learning of deep neural networks: catastrophic forgetting and capacity limitation. To solve the above issues, inspired by the recent breakthroughs in automatically learning good neural network architectures, we develop a Multi-task based lifelong learning via nonexpansive AutoML framework termed Regularize, Expand and Compress (REC). REC is composed of three stages: 1) continually learns the sequential tasks without the learned tasks' data via a newly proposed multi-task weight consolidation (MWC) algorithm; 2) expands the network to help the lifelong learning with potentially improved model capability and performance by network-transformation based AutoML; 3) compresses the expanded model after learning every new task to maintain model efficiency and performance. The proposed MWC and REC algorithms achieve superior performance over other lifelong learning algorithms on four different datasets.
9 pages, 6 figures
References in corpus (11)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Distilling the Knowledge in a Neural Network
- Neural Architecture Search with Reinforcement Learning
- Do Deep Nets Really Need to be Deep?
- PathNet: Evolution Channels Gradient Descent in Super Neural Networks
- Efficient Neural Architecture Search via Parameter Sharing
- Gradient Episodic Memory for Continual Learning
- Efficient Architecture Search by Network Transformation
- Net2Net: Accelerating Learning via Knowledge Transfer
- Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
- Less-forgetful Learning for Domain Expansion in Deep Neural Networks