Intrinsic preservation of plasticity in continual quantum learning

• URL: http://arxiv.org/abs/2511.17228v1
• Date: Fri, 21 Nov 2025 13:14:40 GMT
• Title: Intrinsic preservation of plasticity in continual quantum learning
• Abstract summary: We show that quantum learning models naturally overcome loss of plasticity, preserving plasticity over long timescales.<n>We demonstrate this advantage systematically across a broad spectrum of tasks from multiple learning paradigms.<n>Our results suggest that the utility of quantum computing in machine learning extends beyond potential speedups.
• Score: 0.8312877398178786
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• On the Plasticity Collapse in Continual Machine Unlearning [26.744674850970625]
  Machine unlearning enables networks to selectively remove the influence of specific data in response to privacy and regulatory requirements.<n>While prior work largely studies single-shot unlearning, real-world systems must accommodate continual unlearning.<n>We show that continual unlearning operations accumulate geometric constraints in parameter space, leading to saturated subspaces that restrict future updates.
  arXiv  Detail & Related papers  (2026-08-30T02:33:40Z)
• Modular Memory is the Key to Continual Learning Agents [100.09688599754465]
  We argue that combining the strengths of In-Weight Learning (IWL) and the newly emerged capabilities of In-Context Learning (ICL) through the design of modular memory is the missing piece for continual adaptation at scale.<n>We outline a conceptual framework for modular memory-centric architectures that leverage ICL for rapid adaptation and knowledge accumulation, and IWL for stable updates to model capabilities.
  arXiv  Detail & Related papers  (2026-03-02T11:40:05Z)
• Superior resilience to poisoning and amenability to unlearning in quantum machine learning [0.6445605125467574]
  We show that classical models exhibit brittle memorization, leading to a failure in generalization.<n> quantum models demonstrate remarkable resilience, which is underscored by a phase transition-like response to increasing label noise.<n>Our findings establish that quantum machine learning can possess a dual advantage of intrinsic resilience and efficient adaptability.
  arXiv  Detail & Related papers  (2025-08-04T13:43:47Z)
• The Importance of Being Lazy: Scaling Limits of Continual Learning [60.97756735877614]
  We show that increasing model width is only beneficial when it reduces the amount of feature learning, yielding more laziness.<n>We study the intricate relationship between feature learning, task non-stationarity, and forgetting, finding that high feature learning is only beneficial with highly similar tasks.
  arXiv  Detail & Related papers  (2025-06-20T10:12:38Z)
• Quantum-Inspired Differentiable Integral Neural Networks (QIDINNs): A Feynman-Based Architecture for Continuous Learning Over Streaming Data [0.0]
  Real-time continuous learning over streaming data remains a central challenge in deep learning and AI systems.<n>We introduce a novel architecture, Quantum-Inspired Differentiable Neural Integral Networks (QIDINNs)<n>QIDINNs leverage the Feynman technique of differentiation under the integral sign to formulate neural updates as integrals over historical data.
  arXiv  Detail & Related papers  (2025-06-13T11:00:31Z)
• Conservation-informed Graph Learning for Spatiotemporal Dynamics Prediction [84.26340606752763]
  In this paper, we introduce the conservation-informed GNN (CiGNN), an end-to-end explainable learning framework.<n>The network is designed to conform to the general symmetry conservation law via symmetry where conservative and non-conservative information passes over a multiscale space by a latent temporal marching strategy.<n>Results demonstrate that CiGNN exhibits remarkable baseline accuracy and generalizability, and is readily applicable to learning for prediction of varioustemporal dynamics.
  arXiv  Detail & Related papers  (2024-12-30T13:55:59Z)
• Quantum-Inspired Weight-Constrained Neural Network: Reducing Variable Numbers by 100x Compared to Standard Neural Networks [5.6805708828651]
  We develop a classical weight-constrained neural network that generates weights based on quantum-inspired insights.<n>This approach can reduce the number of variables in a classical neural network by a factor of 135 while preserving its learnability.<n>In addition, we develop a dropout method to enhance the robustness of quantum machine learning models, which are highly susceptible to adversarial attacks.
  arXiv  Detail & Related papers  (2024-12-26T21:35:12Z)
• CTRQNets & LQNets: Continuous Time Recurrent and Liquid Quantum Neural Networks [76.53016529061821]
  Liquid Quantum Neural Network (LQNet) and Continuous Time Recurrent Quantum Neural Network (CTRQNet) developed.<n>LQNet and CTRQNet achieve accuracy increases as high as 40% on CIFAR 10 through binary classification.
  arXiv  Detail & Related papers  (2024-08-28T00:56:03Z)
• Disentangling the Causes of Plasticity Loss in Neural Networks [55.23250269007988]
  We show that loss of plasticity can be decomposed into multiple independent mechanisms. We show that a combination of layer normalization and weight decay is highly effective at maintaining plasticity in a variety of synthetic nonstationary learning tasks.
  arXiv  Detail & Related papers  (2024-02-29T00:02:33Z)
• ShadowNet for Data-Centric Quantum System Learning [188.683909185536]
  We propose a data-centric learning paradigm combining the strength of neural-network protocols and classical shadows. Capitalizing on the generalization power of neural networks, this paradigm can be trained offline and excel at predicting previously unseen systems. We present the instantiation of our paradigm in quantum state tomography and direct fidelity estimation tasks and conduct numerical analysis up to 60 qubits.
  arXiv  Detail & Related papers  (2023-08-22T09:11:53Z)
• The power of quantum neural networks [3.327474729829121]
  In the near-term, however, the benefits of quantum machine learning are not so clear. We use tools from information geometry to define a notion of expressibility for quantum and classical models. We show that quantum neural networks are able to achieve a significantly better effective dimension than comparable classical neural networks.
  arXiv  Detail & Related papers  (2020-10-30T18:13:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.