Quantum continual learning of quantum data realizing knowledge backward transfer

Abstract

For the goal of strong artificial intelligence that can mimic human-level intelligence, AI systems would have the ability to adapt to ever-changing scenarios and learn new knowledge continuously without forgetting previously acquired knowledge. When a machine learning model is consecutively trained on multiple tasks that come in sequence, its performance on previously learned tasks may drop dramatically during the learning process of the newly seen task. To avoid this phenomenon termed catastrophic forgetting, continual learning, also known as lifelong learning, has been proposed and become one of the most up-to-date research areas of machine learning. As quantum machine learning blossoms in recent years, it is interesting to develop quantum continual learning. This paper focuses on the case of quantum models for quantum data where the computation model and the data to be processed are both quantum. The gradient episodic memory method is incorporated to design a quantum continual learning scheme that overcomes catastrophic forgetting and realizes knowledge backward transfer. Specifically, a sequence of quantum state classification tasks is continually learned by a variational quantum classifier whose parameters are optimized by a classical gradient-based optimizer. The gradient of the current task is projected to the closest gradient, avoiding the increase of the loss at previous tasks, but allowing the decrease. Numerical simulation results show that our scheme not only overcomes catastrophic forgetting, but also realize knowledge backward transfer, which means the classifier's performance on previous tasks is enhanced rather than compromised while learning a new task.

References in corpus (31)

• Adam: A Method for Stochastic Optimization
• Quantum Computing in the NISQ era and beyond
• Overcoming catastrophic forgetting in neural networks
• A variational eigenvalue solver on a quantum processor
• Quantum algorithm for solving linear systems of equations
• Supervised learning with quantum enhanced feature spaces
• Quantum support vector machine for big data classification
• A Quantum Approximate Optimization Algorithm
• Quantum machine learning in feature Hilbert spaces
• Quantum Convolutional Neural Networks
• Quantum principal component analysis
• Data re-uploading for a universal quantum classifier
• Quantum Data Fitting
• Quantum Generative Adversarial Networks for Learning and Loading Random Distributions
• Transfer learning in hybrid classical-quantum neural networks
• A generative modeling approach for benchmarking and training shallow quantum circuits
• Quantum-assisted quantum compiling
• Quantum generative adversarial network for generating discrete distribution
• Experimental Realization of a Quantum Autoencoder: The Compression of Qutrits via Machine Learning
• Topological Quantum Compiling with Reinforcement Learning
• Anomaly detection with variational quantum generative adversarial networks
• Realization of a quantum autoencoder for lossless compression of quantum data
• Quantum Wasserstein Generative Adversarial Networks
• Robust resource-efficient quantum variational ansatz through evolutionary algorithm
• Variational quantum compiling with double Q-learning
• Quantum Architecture Search with Meta-learning
• Entangled Datasets for Quantum Machine Learning
• Quantum speedup for twin support vector machines
• GSQAS: Graph Self-supervised Quantum Architecture Search
• Quantum Continual Learning Overcoming Catastrophic Forgetting
• Quantum Architecture Search via Continual Reinforcement Learning