Metraipolis › archive › dc_62e6166d2d12

ReSCENE: Server-Side Replay for Structural Mitigation of Catastrophic Forgetting in Federated Continual Learning — arXiv:2609.38833

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.38833
License (as archived)
CC0-1.0
Archived
2026-10-07T13:45:34.740Z
SHA-256 of the archived text
560d56de29e1895d15531bc97904409f5987207fb8eb205ba7ae61d0c6189731
Stable URL of this page
https://metraipolis.com/documento/dc_62e6166d2d12

How to cite

ReSCENE: Server-Side Replay for Structural Mitigation of Catastrophic Forgetting in Federated Continual Learning — arXiv:2609.38833 — arXiv (en), https://arxiv.org/abs/2609.38833 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_62e6166d2d12 (Metraipolis archive dc_62e6166d2d12, sha256 560d56de29e1895d15531bc97904409f5987207fb8eb205ba7ae61d0c6189731)
BibTeX
@misc{dc62e6166d2d12,
  title = {ReSCENE: Server-Side Replay for Structural Mitigation of Catastrophic Forgetting in Federated Continual Learning — arXiv:2609.38833},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.38833},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_62e6166d2d12; sha256 560d56de29e1895d15531bc97904409f5987207fb8eb205ba7ae61d0c6189731},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38833. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Federated continual learning must integrate new tasks over time without losing earlier-task knowledge. Most existing methods attach an anti-forgetting mechanism to the client-trained, server-aggregated loop of federated learning, which holds back new learning to preserve earlier knowledge and burdens resource-constrained clients. We propose ReSCENE, which structurally mitigates catastrophic forgetting by having each client upload a small condensed surrogate of its local data while the server keeps the surrogates of past tasks and trains the global model on them together with the current task surrogates. For efficient server memory, we introduce temporal herding, which selects the more recent surrogates from the pool accumulated over a task into a compressed buffer. Our study provides a theoretical analysis showing that this buffer can represent the original task data more closely than full accumulation of all surrogates. Across CIFAR-10, CIFAR-100, and TinyImageNet, ReSCENE achieves the strongest accuracy over seven baselines, by up to $31.1$ points of average accuracy, while requiring as little as $0.11\times$ of the client computation and up to $179\times$ less upload than the model-update baselines. ReSCENE further demonstrates its effectiveness when scaled to larger client populations and larger models while remaining efficient, which makes it a practical method for federated continual learning.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.38833 — 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 2026-10-07T13:18:10.268Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).