Metraipolis › archive › dc_9da6580ff9ef

Explain, Then Forget: Recommendation Unlearning under Asymmetric Access Constraint — arXiv:2610.40658

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.40658
License (as archived)
CC0-1.0
Archived
2026-11-03T05:45:34.170Z
SHA-256 of the archived text
f7ab43cfcbf190e8dedede8004a05f61c2dc35fb8298ef79d52bccc8a72bcff4
Stable URL of this page
https://metraipolis.com/documento/dc_9da6580ff9ef

How to cite

Explain, Then Forget: Recommendation Unlearning under Asymmetric Access Constraint — arXiv:2610.40658 — arXiv (en), https://arxiv.org/abs/2610.40658 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9da6580ff9ef (Metraipolis archive dc_9da6580ff9ef, sha256 f7ab43cfcbf190e8dedede8004a05f61c2dc35fb8298ef79d52bccc8a72bcff4)
BibTeX
@misc{dc9da6580ff9ef,
  title = {Explain, Then Forget: Recommendation Unlearning under Asymmetric Access Constraint — arXiv:2610.40658},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40658},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9da6580ff9ef; sha256 f7ab43cfcbf190e8dedede8004a05f61c2dc35fb8298ef79d52bccc8a72bcff4},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40658. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recommendation unlearning aims to remove the influence of specific historical interactions that should no longer affect future recommendations, such as noisy clicks or outdated user preferences. However, performing recommendation unlearning becomes much harder in modern Machine-Learning-as-a-Service (MLaaS) architectures, where the recommendation model is remotely hosted by a model provider (MP) and accessed by service operators (SO) only through APIs. In this setting, a service operator serves end users but cannot access or modify internal model parameters. As a result, existing unlearning methods are difficult to apply because they require access to model internals for retraining, fine-tuning, or other parameter updates. To address these challenges, we propose Causal Explanation-based Unlearning (CEU), a novel unlearning framework tailored for MLaaS environments. Instead of modifying internal model weights, CEU operates through a two-step output-level score intervention. First, it estimates how the forgotten interaction causally contributes to the current recommendation. Second, guided by this causal signal, the system removes the influence of the forgotten interaction by adjusting the final ranking scores of affected items. Because CEU leaves model parameters untouched, it naturally supports continuous unlearning requests while avoiding the error accumulation that can result from repeated parameter updates. Extensive experiments on three public datasets show that CEU achieves unlearning effectiveness comparable to full retraining while preserving recommendation utility and significantly reducing computational cost. The source code is available at: this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2610.40658 — 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 2026-11-03T05:33:19.058Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).