CLAR：面向制造工业互联网灾害诊断的类增量学习新方法
Class-aware Latent Attention Replay (CLAR): Class Incremental Hazard Diagnosis for Resilient AI in the Manufacturing Industrial Internet
工业互联网上灾害种类不断冒新、样本又少，这篇论文的 CLAR 用潜在表示+注意力打分做回放式增量学习，还给了理论证明，搞边缘部署的可以看看。
arXiv 论文提出 Class-aware Latent Attention Replay（CLAR），针对制造工业互联网（MII）中新灾害类型样本少、多灾害共存、计算节点内存受限的场景。方法包含双缓冲区，主要存储压缩潜在表示并保留少量原始样本，用 Attention Leverage Score（ALS）上界约束分类器 logit 并指导类均衡水库采样，同时用指数移动平均教师模型减缓潜在空间漂移。论文对理想化缓冲模型给出证明：缓冲区类均衡并遵循 ALS 加权类分布，低于临界单类容量时 ALS 引导回放比均匀回放的梯度误差更低。在 MII 测试床灾害诊断数据上，CLAR 在相同缓冲区大小下取得评估回放方法中最高的加权平均 F1 分数。
Class-aware Latent Attention Replay (CLAR): Class Incremental Hazard Diagnosis for Resilient AI in the Manufacturing Industrial Internet
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