Metraipolis › archive › dc_eefe2e02c81f

Class-aware Latent Attention Replay (CLAR): Class Incremental Hazard Diagnosis for Resilient AI in the Manufacturing Industrial Internet — arXiv:2610.39323

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.39323
License (as archived): CC0-1.0
Archived: 2026-11-01T02:25:04.049Z
SHA-256 of the archived text: a4886254fef667b131bafcab9de814e916a610c337fd945f857805795c1114fd
Stable URL of this page: https://metraipolis.com/documento/dc_eefe2e02c81f

How to cite

Class-aware Latent Attention Replay (CLAR): Class Incremental Hazard Diagnosis for Resilient AI in the Manufacturing Industrial Internet — arXiv:2610.39323 — arXiv (en), https://arxiv.org/abs/2610.39323 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eefe2e02c81f (Metraipolis archive dc_eefe2e02c81f, sha256 a4886254fef667b131bafcab9de814e916a610c337fd945f857805795c1114fd)

BibTeX

@misc{dceefe2e02c81f,
  title = {Class-aware Latent Attention Replay (CLAR): Class Incremental Hazard Diagnosis for Resilient AI in the Manufacturing Industrial Internet — arXiv:2610.39323},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39323},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eefe2e02c81f; sha256 a4886254fef667b131bafcab9de814e916a610c337fd945f857805795c1114fd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39323. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Artificial Intelligence (AI) systems provide critical computation services in the Manufacturing Industrial Internet (MII), and their resilience depends on timely diagnosis of hazards across the data, AI pipeline, and cyber-physical layers. During operation, new hazard types keep emerging with only a few samples each, hazards co-occur, and the diagnosis model runs on memory-constrained computation nodes. Replay-based class-incremental learning (CIL) can learn new hazard classes while revisiting a small memory of past samples, but existing methods assume single-label, balanced streams, store high-dimensional raw samples, and select them independently of the classifier. We propose Class-aware Latent Attention Replay (CLAR), which combines a dual buffer that stores mostly compact latent representations with a few raw samples, an Attention Leverage Score (ALS) that upper-bounds the classifier logit and guides class-balanced reservoir sampling, and an exponential-moving-average teacher that slows latent-space drift. For an idealized buffer model, we prove that the buffer is class-balanced and follows an ALS-weighted class distribution, and that below a critical per-class capacity, ALS-guided replay has a lower replay-gradient error than class-balanced uniform replay. In the case study, On hazard diagnosis data from an MII testbed, CLAR achieves the highest mean average weighted F1 score among the evaluated replay methods with the same buffer size

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/2610.39323 — 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 2026-11-01T02:12:44.162Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).