Continual Learning via Neural Pruning

Abstract

We introduce Continual Learning via Neural Pruning (CLNP), a new method aimed at lifelong learning in fixed capacity models based on neuronal model sparsification. In this method, subsequent tasks are trained using the inactive neurons and filters of the sparsified network and cause zero deterioration to the performance of previous tasks. In order to deal with the possible compromise between model sparsity and performance, we formalize and incorporate the concept of graceful forgetting: the idea that it is preferable to suffer a small amount of forgetting in a controlled manner if it helps regain network capacity and prevents uncontrolled loss of performance during the training of future tasks. CLNP also provides simple continual learning diagnostic tools in terms of the number of free neurons left for the training of future tasks as well as the number of neurons that are being reused. In particular, we see in experiments that CLNP verifies and automatically takes advantage of the fact that the features of earlier layers are more transferable. We show empirically that CLNP leads to significantly improved results over current weight elasticity based methods.

12 pages, 5 figures, 3 tables

References in corpus (4)

• How transferable are features in deep neural networks?
• Network Trimming: A Data-Driven Neuron Pruning Approach towards Efficient Deep Architectures
• PathNet: Evolution Channels Gradient Descent in Super Neural Networks
• The State of Sparsity in Deep Neural Networks

Cited by in corpus (11)

• Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
• Task Agnostic Continual Learning via Meta Learning
• Dynamically Expandable Graph Convolution for Streaming Recommendation
• Improving and Understanding Variational Continual Learning
• Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics
• Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation
• Bayesian Structure Adaptation for Continual Learning
• Learn-Prune-Share for Lifelong Learning
• Ex uno plures: Splitting One Model into an Ensemble of Subnetworks
• Multi-Scale Weight Sharing Network for Image Recognition
• Emergent Structures and Lifetime Structure Evolution in Artificial Neural Networks