Hybrid Active-Online Learning Framework for Label-Efficient Concept Drift Adaptation in Optical Network Failure Detection
Yousuf Moiz Ali, Jaroslaw E. Prilepsky, João Pedro, Sasipim Srivallapanondh, Antonio Napoli, Sergei K. Turitsyn, Pedro Freire
arXiv:2606.303222.1
Predicted impact top 94% in LG · last 90 daysOriginality Synthesis-oriented
AI Analysis
It addresses the problem of label-efficient concept drift adaptation for optical network operators, but the approach is incremental.
The paper proposes a hybrid active-online learning framework that adapts to concept drift in optical network failure detection, achieving near-ceiling accuracy and AUC while querying only 3.4% of streaming samples with negligible latency overhead.
We propose a hybrid active-online learning framework for label-efficient concept drift adaptation in optical network failure detection. Using margin-based selective labeling, our method achieves nearceiling accuracy and AUC scores while querying only 3.4% of streaming samples, with negligible latency overhead compared to static inference.