Quantum Continual Learning Overcoming Catastrophic Forgetting
arXiv:2108.02786 · doi:10.1088/0256-307X/39/5/050303
Abstract
Catastrophic forgetting describes the fact that machine learning models will likely forget the knowledge of previously learned tasks after the learning process of a new one. It is a vital problem in the continual learning scenario and recently has attracted tremendous concern across different communities. In this paper, we explore the catastrophic forgetting phenomena in the context of quantum machine learning. We find that, similar to those classical learning models based on neural networks, quantum learning systems likewise suffer from such forgetting problem in classification tasks emerging from various application scenes. We show that based on the local geometrical information in the loss function landscape of the trained model, a uniform strategy can be adapted to overcome the forgetting problem in the incremental learning setting. Our results uncover the catastrophic forgetting phenomena in quantum machine learning and offer a practical method to overcome this problem, which opens a new avenue for exploring potential quantum advantages towards continual learning.
References in corpus (11)
- A rigorous and robust quantum speed-up in supervised machine learning
- Information-theoretic bounds on quantum advantage in machine learning
- Measuring Catastrophic Forgetting in Neural Networks
- Experimental quantum speed-up in reinforcement learning agents
- Quantum noise protects quantum classifiers against adversaries
- Machine learning meets quantum physics
- Continual Unsupervised Representation Learning
- Reformulation of the No-Free-Lunch Theorem for Entangled Data Sets
- Realizing a quantum generative adversarial network using a programmable superconducting processor
- Universal Adversarial Examples and Perturbations for Quantum Classifiers
- Continual Learning in Neural Networks