Metraipolis › archive › dc_da16ef9c4ce3

Latent Cluster Separation as a Regularizer for Lifelong Anomaly Detection — arXiv:2611.03652

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03652
License (as archived)
CC0-1.0
Archived
2026-11-04T18:53:42.777Z
SHA-256 of the archived text
6b516f2cbca12a839f65cdd4af08f41d8283c611a28d2241e9747ea76e07dbcc
Stable URL of this page
https://metraipolis.com/documento/dc_da16ef9c4ce3

How to cite

Latent Cluster Separation as a Regularizer for Lifelong Anomaly Detection — arXiv:2611.03652 — arXiv (en), https://arxiv.org/abs/2611.03652 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da16ef9c4ce3 (Metraipolis archive dc_da16ef9c4ce3, sha256 6b516f2cbca12a839f65cdd4af08f41d8283c611a28d2241e9747ea76e07dbcc)
BibTeX
@misc{dcda16ef9c4ce3,
  title = {Latent Cluster Separation as a Regularizer for Lifelong Anomaly Detection — arXiv:2611.03652},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03652},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da16ef9c4ce3; sha256 6b516f2cbca12a839f65cdd4af08f41d8283c611a28d2241e9747ea76e07dbcc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03652. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Lifelong (continual) anomaly detection systems must learn a sequence of tasks without forgetting how to recognize anomaly types seen earlier -- a property known as backward transfer. A common way to try to improve backward transfer is to reshape a model's internal representation around learnable concept centroids, typically coupled with a new way of scoring anomalies based on distance to those centroids. Because these two design choices are usually introduced together, it is unclear which one is actually responsible for any performance gain. In this paper, we unbundle the two mechanisms within a VAE-based lifelong anomaly detector and study them separately. We find that used purely as a training-time regularizer -- while leaving anomaly scoring unchanged -- latent cluster separation can improve detection quality and backward transfer, though whether it outperforms the alternative scoring approach depends on the dataset's underlying representation. Switching to distance-based scoring is instead where most of the instability commonly associated with this class of method actually originates; we identify and explain the underlying mechanism. This benefit depends on the dataset's underlying representation, and we report this as practical guidance for choosing between the two design choices, rather than as a list of caveats.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2611.03652 — 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 2026-11-04T18:35:37.380Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).