A Unified Replay-based Continuous Learning Framework for Spatio-Temporal Prediction on Streaming Data

arXiv:2404.14999v1 Announce Type: cross
Abstract: The widespread deployment of wireless and mobile devices results in a proliferation of spatio-temporal data that is used in applications, e.g., traffic prediction, human mobility mining, and air quality prediction, where spatio-temporal prediction is often essential to enable safety, predictability, or reliability. Many recent proposals that target deep learning for spatio-temporal prediction suffer from so-called catastrophic forgetting, where previously learned knowledge is entirely forgotten when new data arrives. Such proposals may experience deteriorating prediction performance …

abstract air quality applications arxiv continuous cs.db cs.lg data deployment devices framework human mining mobile mobile devices mobility prediction quality reliability results safety streaming streaming data temporal traffic type wireless