Quantum continual learning on a programmable superconducting processor

TL;DR

This paper demonstrates quantum continual learning on a superconducting processor, showing how quantum classifiers can adapt to multiple tasks and retain knowledge using elastic weight consolidation, outperforming classical models in some cases.

Contribution

It provides the first experimental demonstration of quantum continual learning with elastic weight consolidation on a superconducting quantum processor.

Findings

Quantum classifiers suffer from catastrophic forgetting without mitigation.

Elastic weight consolidation enables quantum classifiers to retain knowledge across tasks.

Quantum classifiers outperform classical networks in continual learning with quantum data.

Abstract

Quantum computers may outperform classical computers on machine learning tasks. In recent years, a variety of quantum algorithms promising unparalleled potential to enhance, speed up, or innovate machine learning have been proposed. Yet, quantum learning systems, similar to their classical counterparts, may likewise suffer from the catastrophic forgetting problem, where training a model with new tasks would result in a dramatic performance drop for the previously learned ones. This problem is widely believed to be a crucial obstacle to achieving continual learning of multiple sequential tasks. Here, we report an experimental demonstration of quantum continual learning on a fully programmable superconducting processor. In particular, we sequentially train a quantum classifier with three tasks, two about identifying real-life images and the other on classifying quantum states, and demonstrate its catastrophic forgetting through experimentally observed rapid performance drops for prior tasks. To overcome this dilemma, we exploit the elastic weight consolidation strategy and show that the quantum classifier can incrementally learn and retain knowledge across the three distinct tasks, with an average prediction accuracy exceeding 92.3%. In addition, for sequential tasks involving quantum-engineered data, we demonstrate that the quantum classifier can achieve a better continual learning performance than a commonly used classical feedforward network with a comparable number of variational parameters. Our results establish a viable strategy for empowering quantum learning systems with desirable adaptability to multiple sequential tasks, marking an important primary experimental step towards the long-term goal of achieving quantum artificial general intelligence.