Inductive Spatial Temporal Prediction Under Data Drift with Informative Graph Neural Network
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916402631278592 |
|---|---|
| author | Zheng, Jialun Saxena, Divya Cao, Jiannong Yang, Hanchen Ruan, Penghui |
| author_facet | Zheng, Jialun Saxena, Divya Cao, Jiannong Yang, Hanchen Ruan, Penghui |
| contents | Inductive spatial temporal prediction can generalize historical data to predict unseen data, crucial for highly dynamic scenarios (e.g., traffic systems, stock markets). However, external events (e.g., urban structural growth, market crash) and emerging new entities (e.g., locations, stocks) can undermine prediction accuracy by inducing data drift over time. Most existing studies extract invariant patterns to counter data drift but ignore pattern diversity, exhibiting poor generalization to unseen entities. To address this issue, we design an Informative Graph Neural Network (INF-GNN) to distill diversified invariant patterns and improve prediction accuracy under data drift. Firstly, we build an informative subgraph with a uniquely designed metric, Relation Importance (RI), that can effectively select stable entities and distinct spatial relationships. This subgraph further generalizes new entities' data via neighbors merging. Secondly, we propose an informative temporal memory buffer to help the model emphasize valuable timestamps extracted using influence functions within time intervals. This memory buffer allows INF-GNN to discern influential temporal patterns. Finally, RI loss optimization is designed for pattern consolidation. Extensive experiments on real-world dataset under substantial data drift demonstrate that INF-GNN significantly outperforms existing alternatives. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_13253 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Inductive Spatial Temporal Prediction Under Data Drift with Informative Graph Neural Network Zheng, Jialun Saxena, Divya Cao, Jiannong Yang, Hanchen Ruan, Penghui Machine Learning Inductive spatial temporal prediction can generalize historical data to predict unseen data, crucial for highly dynamic scenarios (e.g., traffic systems, stock markets). However, external events (e.g., urban structural growth, market crash) and emerging new entities (e.g., locations, stocks) can undermine prediction accuracy by inducing data drift over time. Most existing studies extract invariant patterns to counter data drift but ignore pattern diversity, exhibiting poor generalization to unseen entities. To address this issue, we design an Informative Graph Neural Network (INF-GNN) to distill diversified invariant patterns and improve prediction accuracy under data drift. Firstly, we build an informative subgraph with a uniquely designed metric, Relation Importance (RI), that can effectively select stable entities and distinct spatial relationships. This subgraph further generalizes new entities' data via neighbors merging. Secondly, we propose an informative temporal memory buffer to help the model emphasize valuable timestamps extracted using influence functions within time intervals. This memory buffer allows INF-GNN to discern influential temporal patterns. Finally, RI loss optimization is designed for pattern consolidation. Extensive experiments on real-world dataset under substantial data drift demonstrate that INF-GNN significantly outperforms existing alternatives. |
| title | Inductive Spatial Temporal Prediction Under Data Drift with Informative Graph Neural Network |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2409.13253 |