Metraipolis › archive › dc_7cd1f2a02db5

Dynamic Entanglement-Weighted Pruning for Quantum Federated Unlearning in Supply-Chain Risk Prediction — arXiv:2608.17069

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.17069
License (as archived): CC0-1.0
Archived: 2026-10-18T14:48:57.049Z
SHA-256 of the archived text: fec84f1e1bdc5b3d0e149f26fc9fb58eaf4153dc2b9b9d28e40cb20a304bdbbf
Stable URL of this page: https://metraipolis.com/documento/dc_7cd1f2a02db5

How to cite

Dynamic Entanglement-Weighted Pruning for Quantum Federated Unlearning in Supply-Chain Risk Prediction — arXiv:2608.17069 — arXiv (en), https://arxiv.org/abs/2608.17069 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7cd1f2a02db5 (Metraipolis archive dc_7cd1f2a02db5, sha256 fec84f1e1bdc5b3d0e149f26fc9fb58eaf4153dc2b9b9d28e40cb20a304bdbbf)

BibTeX

@misc{dc7cd1f2a02db5,
  title = {Dynamic Entanglement-Weighted Pruning for Quantum Federated Unlearning in Supply-Chain Risk Prediction — arXiv:2608.17069},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.17069},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7cd1f2a02db5; sha256 fec84f1e1bdc5b3d0e149f26fc9fb58eaf4153dc2b9b9d28e40cb20a304bdbbf},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.17069. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Federated deployments of variational quantum classifiers are attractive for cross-organisation risk prediction in supply chains, because raw data never leaves the client, yet data-protection regulations such as the GDPR grant clients a right to request that their contribution be removed from a trained model after the fact. Retraining a federated model from scratch to honour such a request is correct but wasteful, and it is not obvious which quantum circuit parameters actually carry a given client's influence. We introduce Entanglement-Weighted Pruning (EWP), an unlearning procedure for quantum federated learning that scores every trainable circuit parameter with the product of two signals: the diagonal entry of the quantum Fisher information matrix estimated on the target client's data via the parameter-shift rule, and a structural entanglement weight associated with the parameter's gate. Parameters with the lowest scores are pruned, optionally followed by a short fine-tuning pass on the retained clients. We implement the full pipeline in Qiskit for a four-qubit data-re-uploading ansatz trained with FedAvg across five simulated supply-chain-risk clients, and benchmark EWP against full retraining, fine-tuning alone, random pruning, Fisher-only pruning, and entanglement-only pruning, over three random seeds. EWP attains a mean post-unlearning accuracy statistically indistinguishable from the full-retraining oracle, while producing a lower forgetting score and requiring roughly 16 times less wall-clock time. Ablations over pruning threshold, client count, and non-IID strength show that combining the two signals is necessary, as entanglement-only and Fisher-only pruning each substantially degrade accuracy relative to EWP.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-19 in cs.LG).
Categorie arXiv: Quantum Physics (quant-ph) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.17069 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T14:47:59.447Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-19?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).