Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

arXiv:2607.16030

Rethinking Quantum Continual Learning with Quantum Fisher Information

Yu-Chao Hsu, Yu-Cheng Lin, Tai-Yue Li, Nan-Yow Chen, En-Jui Kuo

quant-phcs.AIcs.LGSubmitted Jul 17, 2026• Announced Jul 20, 2026• 0 citations
arXivHTMLPDF

Abstract

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.

Related papers

Experimental demonstration of quantum continual learning with superconducting qubits

Chuanyu Zhang, Zhide Lu, Liangtian Zhao +32 more

Quantum computers may outperform classical computers on machine learning tasks. Yet, quantum learning systems may suffer from catastrophic forgetting, which is widely believed to be an obstacle to achieving continual learning. Here, we report an experimental demonstration of quantum continual learning on a superconducting processor. In particular, we sequentially train a quantum classifier with three tasks, two about identifying real-life images and one on classifying quantum states, and demonstrate its catastrophic forgetting. To overcome this dilemma, we exploit the elastic weight consolidation strategy and show that the quantum classifier can incrementally retain knowledge across three tasks with an average accuracy exceeding 92.3%. Additionally, for sequential tasks involving quantum-engineered data, we demonstrate that the quantum classifier outperforms a classical classifier with a comparable number of parameters. Our results establish a viable strategy for empowering quantum learning systems with adaptability to sequential tasks.

arXiv:2409.09729•npj Quantum Information•Jan 6, 2026•15 citations

Continual Quantum Architecture Search with Tensor-Train Encoding: Theory and Applications to Signal Processing

Jun Qi, Chao-Han Huck Yang, Pin-Yu Chen +3 more

We introduce CL-QAS, a continual quantum architecture search framework that mitigates the challenges of costly amplitude encoding and catastrophic forgetting in variational quantum circuits. The method uses Tensor-Train encoding to efficiently compress high-dimensional stochastic signals into low-rank quantum feature representations. A bi-loop learning strategy separates circuit parameter optimization from architecture exploration, while an Elastic Weight Consolidation regularization ensures stability across sequential tasks. We derive theoretical upper bounds on approximation, generalization, and robustness under quantum noise, demonstrating that CL-QAS achieves controllable expressivity, sample-efficient generalization, and smooth convergence without barren plateaus. Empirical evaluations on electrocardiogram (ECG)-based signal classification and financial time-series forecasting confirm substantial improvements in accuracy, balanced accuracy, F1 score, and reward. CL-QAS maintains strong forward and backward transfer and exhibits bounded degradation under depolarizing and readout noise, highlighting its potential for adaptive, noise-resilient quantum learning on near-term devices.

quant-pharXiv:2601.06392•Jan 13, 2026•0 citations

Dynamic Model Structure Adjustment to Realize Quantum Continual Learning Based on Quantum Data

Hailiang Xu, Haozhen Situ

Catastrophic forgetting emerges when a neural network’s parameters undergo continuous updates during the sequential training of multiple tasks. The ongoing adaptation, while enhancing the model’s suitability for new tasks, inadvertently leads to a degradation in performance on previously learned tasks. This challenge significantly impedes the sequential learning capabilities essential for the advancement of artificial general intelligence. The phenomenon of catastrophic forgetting also occurs in the field of quantum machine learning, where parametric quantum circuits serve a role analogous to neural networks. In this study, our focus is to explore strategies for mitigating catastrophic forgetting within quantum learning models for quantum data. In this context, we employ a task-based hard attention mechanism, which automatically generates masks for each task to regulate the network’s learning process and resist catastrophic forgetting. To our knowledge, the proposed method is the first one in the field of quantum machine learning to adjust the model structure to prevent catastrophic forgetting. Numerical simulation results demonstrate that our approach preserves the model’s performance on previous tasks without compromising its ability to acquire new knowledge. This effective resistance to catastrophic forgetting marks a significant stride in advancing quantum continual learning.

IEEE International Conference on Acoustics Speech and Signal Processing•Mar 18, 2024•1 citation

Quantum Continual Learning Overcoming Catastrophic Forgetting

Wenjie Jiang, Zhide Lu, Dong-Ling Deng

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. We explore the catastrophic forgetting phenomena in the context of quantum machine learning. It is found 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.

arXiv:2108.02786•Chinese Physics Letters•May 1, 2022•18 citations

Adaptive Noise-Aware Variational Quantum Classifier for Robust Machine Learning on NISQ Devices

Vinodh Kumar S, Pravin P

The execution of Variational Quantum Algorithms on Noisy Intermediate-Scale Quantum hardware is severely impacted by hardware noise variations over time and decoherence. This work introduces an Adaptive Noise-Aware Variational Quantum Classifier (ANAVQC) that integrates Zero-Noise Extrapolation (ZNE) dynamically into the training loop to counter variations. The framework approximates the instantaneous depolarizing noise from calibration and adapts noise scaling and linear extrapolation to estimate noise-free expectation values at training. A two-qubit parameterized quantum circuit is built and simulated in MATLAB, with the inclusion of stochastic gradient descent coupled with parameter-shift-based gradients. The model is conditioned on a synthetic binary classification data under a time-varying depolarizing noise profile and exhibits improved convergence stability and classification accuracy over non-adaptive methods. The simulation results identify that adaptive ZNE increases model robustness against time-varying noise and offers a scalable route to reliable quantum machine learning on practical NISQ hardware. The current ANAVQC scheme is extendable to multi-qubit platforms and practical quantum backends for the purposes of future experimental testing.

International Conference on Intelligent Computing and Automation for Sustainable Solutions (ICASS)•Feb 12, 2026•0 citations

Intrinsic preservation of plasticity in continual quantum learning

Yu-Qin Chen, Shi-Xin Zhang

Artificial intelligence in dynamic, real-world environments requires the capacity for continual learning. However, standard deep learning suffers from a fundamental issue: loss of plasticity, in which networks gradually lose their ability to learn from new data. Here we show that quantum learning models naturally overcome this limitation, preserving plasticity over long timescales. We demonstrate this advantage systematically across a broad spectrum of tasks from multiple learning paradigms, including supervised learning and reinforcement learning, and diverse data modalities, from classical high-dimensional images to quantum-native datasets. Although classical models exhibit performance degradation correlated with unbounded weight and gradient growth, quantum neural networks maintain consistent learning capabilities regardless of the data or task. We identify the origin of the advantage as the intrinsic physical constraints of quantum models. Unlike classical networks where unbounded weight growth leads to landscape ruggedness or saturation, the unitary constraints confine the optimization to a compact manifold. Our results suggest that the utility of quantum computing in machine learning extends beyond potential speedups, offering a robust pathway for building adaptive artificial intelligence and lifelong learners.

quant-pharXiv:2511.17228•PRX Quantum•Nov 24, 2025•4 citations
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.
Quantum computers may outperform classical computers on machine learning tasks. Yet, quantum learning systems may suffer from catastrophic forgetting, which is widely believed to be an obstacle to achieving continual learning. Here, we report an experimental demonstration of quantum continual learning on a superconducting processor. In particular, we sequentially train a quantum classifier with three tasks, two about identifying real-life images and one on classifying quantum states, and demonstrate its catastrophic forgetting. To overcome this dilemma, we exploit the elastic weight consolidation strategy and show that the quantum classifier can incrementally retain knowledge across three tasks with an average accuracy exceeding 92.3%. Additionally, for sequential tasks involving quantum-engineered data, we demonstrate that the quantum classifier outperforms a classical classifier with a comparable number of parameters. Our results establish a viable strategy for empowering quantum learning systems with adaptability to sequential tasks.
We introduce CL-QAS, a continual quantum architecture search framework that mitigates the challenges of costly amplitude encoding and catastrophic forgetting in variational quantum circuits. The method uses Tensor-Train encoding to efficiently compress high-dimensional stochastic signals into low-rank quantum feature representations. A bi-loop learning strategy separates circuit parameter optimization from architecture exploration, while an Elastic Weight Consolidation regularization ensures stability across sequential tasks. We derive theoretical upper bounds on approximation, generalization, and robustness under quantum noise, demonstrating that CL-QAS achieves controllable expressivity, sample-efficient generalization, and smooth convergence without barren plateaus. Empirical evaluations on electrocardiogram (ECG)-based signal classification and financial time-series forecasting confirm substantial improvements in accuracy, balanced accuracy, F1 score, and reward. CL-QAS maintains strong forward and backward transfer and exhibits bounded degradation under depolarizing and readout noise, highlighting its potential for adaptive, noise-resilient quantum learning on near-term devices.
Catastrophic forgetting emerges when a neural network’s parameters undergo continuous updates during the sequential training of multiple tasks. The ongoing adaptation, while enhancing the model’s suitability for new tasks, inadvertently leads to a degradation in performance on previously learned tasks. This challenge significantly impedes the sequential learning capabilities essential for the advancement of artificial general intelligence. The phenomenon of catastrophic forgetting also occurs in the field of quantum machine learning, where parametric quantum circuits serve a role analogous to neural networks. In this study, our focus is to explore strategies for mitigating catastrophic forgetting within quantum learning models for quantum data. In this context, we employ a task-based hard attention mechanism, which automatically generates masks for each task to regulate the network’s learning process and resist catastrophic forgetting. To our knowledge, the proposed method is the first one in the field of quantum machine learning to adjust the model structure to prevent catastrophic forgetting. Numerical simulation results demonstrate that our approach preserves the model’s performance on previous tasks without compromising its ability to acquire new knowledge. This effective resistance to catastrophic forgetting marks a significant stride in advancing quantum continual learning.
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. We explore the catastrophic forgetting phenomena in the context of quantum machine learning. It is found 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.
The execution of Variational Quantum Algorithms on Noisy Intermediate-Scale Quantum hardware is severely impacted by hardware noise variations over time and decoherence. This work introduces an Adaptive Noise-Aware Variational Quantum Classifier (ANAVQC) that integrates Zero-Noise Extrapolation (ZNE) dynamically into the training loop to counter variations. The framework approximates the instantaneous depolarizing noise from calibration and adapts noise scaling and linear extrapolation to estimate noise-free expectation values at training. A two-qubit parameterized quantum circuit is built and simulated in MATLAB, with the inclusion of stochastic gradient descent coupled with parameter-shift-based gradients. The model is conditioned on a synthetic binary classification data under a time-varying depolarizing noise profile and exhibits improved convergence stability and classification accuracy over non-adaptive methods. The simulation results identify that adaptive ZNE increases model robustness against time-varying noise and offers a scalable route to reliable quantum machine learning on practical NISQ hardware. The current ANAVQC scheme is extendable to multi-qubit platforms and practical quantum backends for the purposes of future experimental testing.
Artificial intelligence in dynamic, real-world environments requires the capacity for continual learning. However, standard deep learning suffers from a fundamental issue: loss of plasticity, in which networks gradually lose their ability to learn from new data. Here we show that quantum learning models naturally overcome this limitation, preserving plasticity over long timescales. We demonstrate this advantage systematically across a broad spectrum of tasks from multiple learning paradigms, including supervised learning and reinforcement learning, and diverse data modalities, from classical high-dimensional images to quantum-native datasets. Although classical models exhibit performance degradation correlated with unbounded weight and gradient growth, quantum neural networks maintain consistent learning capabilities regardless of the data or task. We identify the origin of the advantage as the intrinsic physical constraints of quantum models. Unlike classical networks where unbounded weight growth leads to landscape ruggedness or saturation, the unitary constraints confine the optimization to a compact manifold. Our results suggest that the utility of quantum computing in machine learning extends beyond potential speedups, offering a robust pathway for building adaptive artificial intelligence and lifelong learners.