Quantum Continual Learning Overcoming Catastrophic Forgetting

TL;DR

This paper investigates catastrophic forgetting in quantum machine learning, demonstrating its occurrence and proposing a geometrically-informed strategy to mitigate it, thereby advancing quantum continual learning capabilities.

Contribution

It uncovers the presence of catastrophic forgetting in quantum models and introduces a practical, geometry-based method to overcome it in incremental learning scenarios.

Findings

Quantum models suffer from catastrophic forgetting in classification tasks.

A geometry-based strategy effectively mitigates forgetting in quantum learning.

The approach opens new possibilities for quantum advantages in continual learning.

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.