Novel Node Category Detection Under Subpopulation Shift
This addresses the need for safety or insight discovery in real-world graph data where distribution shifts occur, such as new categories emerging, but it appears incremental as it builds on existing detection methods.
The paper tackles the problem of detecting nodes belonging to novel categories in attributed graphs under subpopulation shifts, introducing RECO-SLIP, which shows superior performance over existing methods in empirical evaluations across multiple datasets.
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.