Metraipolis › archive › dc_a0cd0de29354
SPACE-LoRA: Allocating Activation-Subspace Protection for Continual Learning — arXiv:2609.34453
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34453
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T21:02:36.573Z
- SHA-256 of the archived text
566750c1b039466f15c56c3deeacc1f2a550d87e2b8f347741912120d4815688- Stable URL of this page
https://metraipolis.com/documento/dc_a0cd0de29354
How to cite
SPACE-LoRA: Allocating Activation-Subspace Protection for Continual Learning — arXiv:2609.34453 — arXiv (en), https://arxiv.org/abs/2609.34453 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a0cd0de29354 (Metraipolis archive dc_a0cd0de29354, sha256 566750c1b039466f15c56c3deeacc1f2a550d87e2b8f347741912120d4815688)
BibTeX
@misc{dca0cd0de29354,
title = {SPACE-LoRA: Allocating Activation-Subspace Protection for Continual Learning — arXiv:2609.34453},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34453},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a0cd0de29354; sha256 566750c1b039466f15c56c3deeacc1f2a550d87e2b8f347741912120d4815688},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34453. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
This study addresses the catastrophic forgetting problem that occurs when sequentially learning successive tasks using Low-Rank Adaptation (LoRA) from a lifelong learning perspective. While existing approaches have primarily constrained parameter updates or learning subspaces to reduce interference with past knowledge, they have not fully considered additive interference. This occurs when a newly added residual adapter on top of a fixed past model generates non-zero responses along input directions important for old tasks, thereby altering previous predictions. To this end, we propose Subspace Protection with Allocated Capacity for Efficient Continual Adaptation (SPACE-LoRA). SPACE-LoRA directly suppresses the responses of the new residual branch along input activation directions that are important for old tasks and adaptively determines the protection coverage for each module based on past-task sensitivity estimated via a common Fisher sensitivity-based coverage target. Under a fixed LoRA rank, this approach adaptively adjusts module-specific protection coverage while suppressing interference along input directions sensitive to old tasks. We assess the effectiveness of activation-subspace protection in mitigating catastrophic forgetting and examine the role of sensitivity-guided protection in continual learning across diverse tasks. Code is available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.34453 — 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 2026-10-07T20:29:02.999Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).