Adaptive Progressive Continual Learning

Continual learning paradigm learns from a continuous stream of tasks in an incremental manner and aims to overcome the notorious issue: the catastrophic forgetting. In this work, we propose a new adaptive progressive network framework including two models for continual learning: Reinforced Continual...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on pattern analysis and machine intelligence 2022-10, Vol.44 (10), p.6715-6728
Main Authors: Xu, Ju, Ma, Jin, Gao, Xuesong, Zhu, Zhanxing
Format: Article
Language:English
Subjects:
adaptive progressive network framework
Bayes methods
Bayesian analysis
Bayesian optimization
Complexity theory
continual learning
Control methods
Feature maps
Initiatives
Knowledge engineering
Machine learning
Neural networks
Optimization
Reinforcement learning
Task analysis
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Continual learning paradigm learns from a continuous stream of tasks in an incremental manner and aims to overcome the notorious issue: the catastrophic forgetting. In this work, we propose a new adaptive progressive network framework including two models for continual learning: Reinforced Continual Learning (RCL) and Bayesian Optimized Continual Learning with Attention mechanism (BOCL) to solve this fundamental issue. The core idea of this framework is to dynamically and adaptively expand the neural network structure upon the arrival of new tasks. RCL and BOCL employ reinforcement learning and Bayesian optimization to achieve it, respectively. An outstanding advantage of our proposed framework is that it will not forget the knowledge that has been learned through adaptively controlling the architecture. We propose effective ways of employing the learned knowledge in the two methods to control the size of the network. RCL employs previous knowledge directly while BOCL selectively utilizes previous knowledge (e.g., feature maps of previous tasks) via attention mechanism. The experiments on variants of MNIST, CIFAR-100 and Sequence of 5-Datasets demonstrate that our methods outperform the state-of-the-art in preventing catastrophic forgetting and fitting new tasks better under the same or less computing resource.
ISSN:0162-8828
2160-9292
1939-3539
DOI:10.1109/TPAMI.2021.3095064