Novel Node Category Detection Under Subpopulation Shift

Autor:	Chung, Hsing-Huan, Chaudhari, Shravan, Wald, Yoav, Han, Xing, Ghosh, Joydeep
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Computer Science - Social and Information Networks Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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 recall-constrained learning framework with a sample-efficient link prediction mechanism, RECO-SLIP addresses the dual challenges of resilience against subpopulation shifts and the effective exploitation of graph structure. Our extensive empirical evaluation across multiple graph datasets demonstrates the superior performance of RECO-SLIP over existing methods. The experimental code is available at https://github.com/hsinghuan/novel-node-category-detection. Comment: Accepted to ECML-PKDD 2024
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2404.01216 Zobrazit plný text záznamu View this record from Arxiv