Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting

Abstract

Addressing catastrophic forgetting is one of the key challenges in continual learning where machine learning systems are trained with sequential or streaming tasks. Despite recent remarkable progress in state-of-the-art deep learning, deep neural networks (DNNs) are still plagued with the catastrophic forgetting problem. This paper presents a conceptually simple yet general and effective framework for handling catastrophic forgetting in continual learning with DNNs. The proposed method consists of two components: a neural structure optimization component and a parameter learning and/or fine-tuning component. By separating the explicit neural structure learning and the parameter estimation, not only is the proposed method capable of evolving neural structures in an intuitively meaningful way, but also shows strong capabilities of alleviating catastrophic forgetting in experiments. Furthermore, the proposed method outperforms all other baselines on the permuted MNIST dataset, the split CIFAR100 dataset and the Visual Domain Decathlon dataset in continual learning setting.

References in corpus (2)

• Neural Architecture Search with Reinforcement Learning
• PathNet: Evolution Channels Gradient Descent in Super Neural Networks

Cited by in corpus (19)

• Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
• A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning
• Understanding the Role of Training Regimes in Continual Learning
• Continual Learning of a Mixed Sequence of Similar and Dissimilar Tasks
• Orthogonal Gradient Descent for Continual Learning
• Gradient Projection Memory for Continual Learning
• Continual Learning via Inter-Task Synaptic Mapping
• Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics
• The Effectiveness of Memory Replay in Large Scale Continual Learning
• Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation
• Bayesian Structure Adaptation for Continual Learning
• Lifelong Learning using Eigentasks: Task Separation, Skill Acquisition, and Selective Transfer
• Task-agnostic Continual Learning with Hybrid Probabilistic Models
• Bilevel Continual Learning
• Continual Learning in Task-Oriented Dialogue Systems
• Incremental Learning via Rate Reduction
• Towards Robust Pattern Recognition: A Review
• Discriminative Distillation to Reduce Class Confusion in Continual Learning
• A Meta-Learned Neuron model for Continual Learning