Liquid Neural Network-based Adaptive Learning vs. Incremental Learning for Link Load Prediction amid Concept Drift due to Network Failures

arXiv:2404.05304v1 Announce Type: cross
Abstract: Adapting to concept drift is a challenging task in machine learning, which is usually tackled using incremental learning techniques that periodically re-fit a learning model leveraging newly available data. A primary limitation of these techniques is their reliance on substantial amounts of data for retraining. The necessity of acquiring fresh data introduces temporal delays prior to retraining, potentially rendering the models inaccurate if a sudden concept drift occurs in-between two consecutive retrainings. In communication networks, …

abstract arxiv concept cs.lg cs.ni data drift incremental machine machine learning network neural network prediction type