Novel Node Category Detection Under Subpopulation Shift
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866917708627443712 |
|---|---|
| author | Chung, Hsing-Huan Chaudhari, Shravan Wald, Yoav Han, Xing Ghosh, Joydeep |
| author_facet | Chung, Hsing-Huan Chaudhari, Shravan Wald, Yoav Han, Xing Ghosh, Joydeep |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_01216 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Novel Node Category Detection Under Subpopulation Shift Chung, Hsing-Huan Chaudhari, Shravan Wald, Yoav Han, Xing Ghosh, Joydeep Machine Learning Social and Information Networks 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. |
| title | Novel Node Category Detection Under Subpopulation Shift |
| topic | Machine Learning Social and Information Networks |
| url | https://arxiv.org/abs/2404.01216 |