Quantum Continual Learning Overcoming Catastrophic Forgetting

• URL: http://arxiv.org/abs/2108.02786v1
• Date: Thu, 5 Aug 2021 18:00:03 GMT
• Title: Quantum Continual Learning Overcoming Catastrophic Forgetting
• Abstract summary: 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. 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.
• Score: 1.1344265020822928
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Quantum Adversarial Machine Learning: From Classical Adaptations to Quantum-Native Methods [1.343545267835616]
  Adversarial machine learning studies vulnerabilities to build robust machine learning models.<n>We provide a detailed overview on quantum adversarial machine learning and explore the existing attacks and countermeasures.
  arXiv  Detail & Related papers  (2026-05-12T14:41:20Z)
• Old Rules in a New Game: Mapping Uncertainty Quantification to Quantum Machine Learning [0.0]
  Despite significant research in classical contexts, there has been little advancement in addressing the black-box nature of quantum machine learning.<n>Our findings emphasize the necessity of leveraging classical insights into uncertainty quantification to include uncertainty awareness in the process of designing new quantum machine learning models.
  arXiv  Detail & Related papers  (2025-07-20T11:16:56Z)
• 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)
• Exponential separations between classical and quantum learners [2.209921757303168]
  We discuss how subtle differences in definitions can result in significantly different requirements and tasks for the learner to meet and solve. We present two new learning separations where the classical difficulty primarily lies in identifying the function generating the data.
  arXiv  Detail & Related papers  (2023-06-28T08:55:56Z)
• A didactic approach to quantum machine learning with a single qubit [68.8204255655161]
  We focus on the case of learning with a single qubit, using data re-uploading techniques. We implement the different proposed formulations in toy and real-world datasets using the qiskit quantum computing SDK.
  arXiv  Detail & Related papers  (2022-11-23T18:25:32Z)
• Anti-Retroactive Interference for Lifelong Learning [65.50683752919089]
  We design a paradigm for lifelong learning based on meta-learning and associative mechanism of the brain. It tackles the problem from two aspects: extracting knowledge and memorizing knowledge. It is theoretically analyzed that the proposed learning paradigm can make the models of different tasks converge to the same optimum.
  arXiv  Detail & Related papers  (2022-08-27T09:27:36Z)
• On establishing learning separations between classical and quantum machine learning with classical data [0.0]
  We discuss the challenges of finding learning problems that quantum learning algorithms can learn much faster than any classical learning algorithm. We study existing learning problems with a provable quantum speedup to distill sets of more general and sufficient conditions. These checklists are intended to streamline one's approach to proving quantum speedups for learning problems, or to elucidate bottlenecks.
  arXiv  Detail & Related papers  (2022-08-12T16:00:30Z)
• Embedding Learning in Hybrid Quantum-Classical Neural Networks [8.029801398363261]
  We propose a quantum few-shot embedding learning paradigm, which learns embeddings useful for training downstream quantum machine learning tasks. We identify the circuit bypass problem in hybrid neural networks, where learned classical parameters do not utilize the Hilbert space efficiently. We observe that the few-shot learned embeddings generalize to unseen classes and suffer less from the circuit bypass problem compared with other approaches.
  arXiv  Detail & Related papers  (2022-04-09T21:16:20Z)
• Modern applications of machine learning in quantum sciences [51.09906911582811]
  We cover the use of deep learning and kernel methods in supervised, unsupervised, and reinforcement learning algorithms. We discuss more specialized topics such as differentiable programming, generative models, statistical approach to machine learning, and quantum machine learning.
  arXiv  Detail & Related papers  (2022-04-08T17:48:59Z)
• Continual learning of quantum state classification with gradient episodic memory [0.20646127669654826]
  A phenomenon called catastrophic forgetting emerges when a machine learning model is trained across multiple tasks. Some continual learning strategies have been proposed to address the catastrophic forgetting problem. In this work, we incorporate the gradient episodic memory method to train a variational quantum classifier.
  arXiv  Detail & Related papers  (2022-03-26T09:28:26Z)
• Knowledge as Invariance -- History and Perspectives of Knowledge-augmented Machine Learning [69.99522650448213]
  Research in machine learning is at a turning point. Research interests are shifting away from increasing the performance of highly parameterized models to exceedingly specific tasks. This white paper provides an introduction and discussion of this emerging field in machine learning research.
  arXiv  Detail & Related papers  (2020-12-21T15:07:19Z)
• Few-Shot Class-Incremental Learning [68.75462849428196]
  We focus on a challenging but practical few-shot class-incremental learning (FSCIL) problem. FSCIL requires CNN models to incrementally learn new classes from very few labelled samples, without forgetting the previously learned ones. We represent the knowledge using a neural gas (NG) network, which can learn and preserve the topology of the feature manifold formed by different classes.
  arXiv  Detail & Related papers  (2020-04-23T03:38:33Z)
• Quantum Adversarial Machine Learning [0.0]
  Adrial machine learning is an emerging field that focuses on studying vulnerabilities of machine learning approaches in adversarial settings. In this paper, we explore different adversarial scenarios in the context of quantum machine learning. We find that a quantum classifier that achieves nearly the state-of-the-art accuracy can be conclusively deceived by adversarial examples.
  arXiv  Detail & Related papers  (2019-12-31T19:00:12Z)

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.