Rethinking Quantum Continual Learning with Quantum Fisher Information
Not on the map. Why?
Abstract (arXiv)
Quantum continual learning aims to train quantum models on sequential tasks without losing previously learned knowledge. However, variational quantum classifiers (VQCs) are prone to catastrophic forgetting under nonstationary task distributions. We propose quantum elastic weight consolidation (QEWC), a quantum Fisher information (QFI)-informed regularization method for mitigating forgetting. Unlike conventional elastic weight consolidation based on classical Fisher information (CFI), which measures parameter importance through measurement-dependent output statistics, QEWC uses QFI to quantify the intrinsic sensitivity of the parameterized quantum state. This gives an information-geometric view in which important parameters are identified by the local response of the quantum state manifold. We evaluate QEWC on VQCs trained on sequential binary classification tasks, including classical image-classification and quantum phase-classification tasks. Simulations show that sequential training without regularization causes severe forgetting, while both CFI-based EWC and QFI-based QEWC improve retention of previous tasks. Mechanistic analyses further show that the two methods impose different regularization geometries: CFI acts selectively on measurement-sensitive directions, whereas QFI imposes a denser state-geometric constraint over parameter space. Under depolarizing noise, CFI values are strongly suppressed by degraded measurement statistics, while QFI preserves a more stable sensitivity structure of the noisy parameterized quantum state. These results establish QEWC as a physically motivated approach for studying and mitigating forgetting in quantum continual learning through quantum-state geometry.
Key facts. No citing papers in the map yet (data through 13 Oct 2026). Builds on 20 of its 55 references that are in the map. First posted on arXiv 17 Jul 2026.
Builds on
20 of 55 references.
References · 20
- 2016Overcoming catastrophic forgetting in neural networkscited by 4,753
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,328
- 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,322
- 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 862
- 2013An Empirical Investigation of Catastrophic Forgetting in Gradient-Based Neural Networkscited by 718
- 2018Supervised learning with quantum enhanced feature spacescited by 660
- 2020The power of quantum neural networkscited by 378
- 2017Measuring Catastrophic Forgetting in Neural Networkscited by 360
- 2019Parameterized quantum circuits as machine learning modelscited by 332
- 2019Efficient Learning for Deep Quantum Neural Networkscited by 160
- 2019Quantum Natural Gradientcited by 106
- 2024Validating Large-Scale Quantum Machine Learning: Efficient Simulation of Quantum Support Vector Machines Using Tensor Networkscited by 16
8 more
- 2020Neural-Network Heuristics for Adaptive Bayesian Quantum Estimationcited by 7
- 2021Quantum Continual Learning Overcoming Catastrophic Forgettingcited by 7
- 2023Evaluating Continual Learning on a Home Robotcited by 5
- 2024Continual Learning for Autonomous Robots: A Prototype-based Approachcited by 5
- 2018Continual Learning Augmented Investment Decisionscited by 3
- 2024Quantum Pointwise Convolution: A Flexible and Scalable Approach for Neural Network Enhancementcited by 3
- 2026QCL-IDS: Quantum Continual Learning for Intrusion Detection with Fidelity-Anchored Stability and Generative Replaycited by 2
- 2025Intrinsic preservation of plasticity in continual quantum learningcited by 1
Built on by
Not cited yet.