Metraipolis › archive › dc_d15185d78747

Don't Just Impute, Detect: Task-Aware Diffusion Pipelines for Edge Anomaly Detection — arXiv:2610.40732

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.40732
License (as archived): CC0-1.0
Archived: 2026-11-03T08:11:37.360Z
SHA-256 of the archived text: c624d37887335e7db635225a57c463fb2f5a7f8b29c234eff14e7d3bd16aab63
Stable URL of this page: https://metraipolis.com/documento/dc_d15185d78747

How to cite

Don't Just Impute, Detect: Task-Aware Diffusion Pipelines for Edge Anomaly Detection — arXiv:2610.40732 — arXiv (en), https://arxiv.org/abs/2610.40732 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d15185d78747 (Metraipolis archive dc_d15185d78747, sha256 c624d37887335e7db635225a57c463fb2f5a7f8b29c234eff14e7d3bd16aab63)

BibTeX

@misc{dcd15185d78747,
  title = {Don't Just Impute, Detect: Task-Aware Diffusion Pipelines for Edge Anomaly Detection — arXiv:2610.40732},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40732},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d15185d78747; sha256 c624d37887335e7db635225a57c463fb2f5a7f8b29c234eff14e7d3bd16aab63},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40732. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Industrial Internet of Things (IIoT) edge pipelines routinely lose contiguous blocks of multi-sensor data to network dropouts and hardware faults. The standard remedy is a disjointed "impute-then-detect" pipeline whose imputer is trained only for Mean Squared Error (MSE). Such an imputer fills a missing block with the most probable normal pattern: a partially observed anomaly is smoothed back toward normality, and boundary artifacts on normal data raise false alarms. We call this imputation bias and propose the Task-Aware Diffusion Refiner (TADR), a conditional diffusion refiner trained against the loss landscape of a frozen downstream detector. Because back-propagating through the sampling trajectory is intractable, the task-aware terms act on the one-step clean-window estimate that the noise prediction already yields, so training costs no more than plain diffusion training. Under strict Point-to-Point evaluation over five seeds with paired significance tests, TADR raises F1 by $0.338$ over the unrefined detector on SMD ($p = 0.0015$), and the anomaly enhancement objective alone contributes $0.463$ in ablation. We also characterise when the method helps: the gain tracks the continuous, mutually redundant channels available and the anomaly evidence the outage removes, and it is absent on telemetry datasets dominated by one-hot command channels and on PSM. At ten sampling steps TADR runs in $41.4$ ms per window on a single CPU core, sustaining about $24$ concurrent 1 Hz streams from a $4.03$ MB model. Code and per-seed results are available at this https URL .

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/2610.40732 — 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 2026-11-03T08:02:38.890Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).