PlugSI: Plug-and-Play Test-Time Graph Adaptation for Spatial Interpolation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866914319343550464 |
|---|---|
| author | Wu, Xuhang Liang, Zhuoxuan Li, Wei Jia, Xiaohua Helal, Sumi |
| author_facet | Wu, Xuhang Liang, Zhuoxuan Li, Wei Jia, Xiaohua Helal, Sumi |
| contents | With the rapid advancement of IoT and edge computing, sensor networks have become indispensable, driving the need for large-scale sensor deployment. However, the high deployment cost hinders their scalability. To tackle the issues, Spatial Interpolation (SI) introduces virtual sensors to infer readings from observed sensors, leveraging graph structure. However, current graph-based SI methods rely on pre-trained models, lack adaptation to larger and unseen graphs at test-time, and overlook test data utilization. To address these issues, we propose PlugSI, a plug-and-play framework that refines test-time graph through two key innovations. First, we design an Unknown Topology Adapter (UTA) that adapts to the new graph structure of each small-batch at test-time, enhancing the generalization of SI pre-trained models. Second, we introduce a Temporal Balance Adapter (TBA) that maintains a stable historical consensus to guide UTA adaptation and prevent drifting caused by noise in the current batch. Empirically, extensive experiments demonstrate PlugSI can be seamlessly integrated into existing graph-based SI methods and provide significant improvement (e.g., a 10.81% reduction in MAE). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_09824 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PlugSI: Plug-and-Play Test-Time Graph Adaptation for Spatial Interpolation Wu, Xuhang Liang, Zhuoxuan Li, Wei Jia, Xiaohua Helal, Sumi Machine Learning With the rapid advancement of IoT and edge computing, sensor networks have become indispensable, driving the need for large-scale sensor deployment. However, the high deployment cost hinders their scalability. To tackle the issues, Spatial Interpolation (SI) introduces virtual sensors to infer readings from observed sensors, leveraging graph structure. However, current graph-based SI methods rely on pre-trained models, lack adaptation to larger and unseen graphs at test-time, and overlook test data utilization. To address these issues, we propose PlugSI, a plug-and-play framework that refines test-time graph through two key innovations. First, we design an Unknown Topology Adapter (UTA) that adapts to the new graph structure of each small-batch at test-time, enhancing the generalization of SI pre-trained models. Second, we introduce a Temporal Balance Adapter (TBA) that maintains a stable historical consensus to guide UTA adaptation and prevent drifting caused by noise in the current batch. Empirically, extensive experiments demonstrate PlugSI can be seamlessly integrated into existing graph-based SI methods and provide significant improvement (e.g., a 10.81% reduction in MAE). |
| title | PlugSI: Plug-and-Play Test-Time Graph Adaptation for Spatial Interpolation |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2602.09824 |