PlugSI: Plug-and-Play Test-Time Graph Adaptation for Spatial Interpolation

2026-02-10

AI Summary

This work addresses the limited generalization of existing graph neural networks (GNNs) in spatiotemporal interpolation tasks, particularly when encountering unseen or larger-scale graph structures, as well as their inability to dynamically leverage test-time data. To overcome these limitations, we propose a plug-and-play test-time graph adaptation framework comprising an Unknown Topology Adapter (UTA) that dynamically adjusts to mini-batch graph structures at inference time, and a Temporal Balancing Adapter (TBA) that mitigates noise-induced drift through historical consistency constraints. By seamlessly integrating GNNs with test-time adaptation and temporal coherence mechanisms, our approach significantly enhances interpolation performance across multiple benchmarks, achieving an average reduction of 10.81% in mean absolute error (MAE).

Technology Category

• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Temporal Planning
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

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).

Problem

• Spatial Interpolation
• Graph Adaptation
• Test-Time Adaptation
• Sensor Networks
• Plug-and-Play

Innovation

• Plug-and-Play
• Test-Time Adaptation
• Graph Neural Networks
• Spatial Interpolation
• Unknown Topology Adapter