Novel Node Category Detection Under Subpopulation Shift

arXiv:2404.01216v1 Announce Type: new
Abstract: In real-world graph data, distribution shifts can manifest in various ways, such as the emergence of new categories and changes in the relative proportions of existing categories. It is often important to detect nodes of novel categories under such distribution shifts for safety or insight discovery purposes. We introduce a new approach, Recall-Constrained Optimization with Selective Link Prediction (RECO-SLIP), to detect nodes belonging to novel categories in attributed graphs under subpopulation shifts. By integrating a …

abstract arxiv cs.lg cs.si data detection discovery distribution emergence graph graph data insight manifest node nodes novel safety shift stat.ml type world