DarkFarseer: Robust Spatio-temporal Kriging under Graph Sparsity and Noise

TL;DR

DarkFarseer addresses robust inductive spatio-temporal kriging under graph sparsity and noise by introducing a temporal-first SeTS architecture, region-aware RsCL, and edge-denoising SGDs. SeTS enhances virtual-node representations by transferring temporal fluctuation styles from 1-hop physical neighbors, while RsCL leverages regional prototypes from BCCs to align virtual-node patterns with regional semantics. SGDs downweights noisy edges based on temporal-prototype similarity, improving the effectiveness of subsequent message passing. Across five real-world datasets with varying graph topologies, DarkFarseer achieves state-of-the-art accuracy and demonstrates robustness to masking and parameter variations, providing a scalable solution for fine-grained sensing with virtual sensors in IoT/CPS.

Abstract

With the rapid growth of the Internet of Things and Cyber-Physical Systems, widespread sensor deployment has become essential. However, the high costs of building sensor networks limit their scale and coverage, making fine-grained deployment challenging. Inductive Spatio-Temporal Kriging (ISK) addresses this issue by introducing virtual sensors. Based on graph neural networks (GNNs) extracting the relationships between physical and virtual sensors, ISK can infer the measurements of virtual sensors from physical sensors. However, current ISK methods rely on conventional message-passing mechanisms and network architectures, without effectively extracting spatio-temporal features of physical sensors and focusing on representing virtual sensors. Additionally, existing graph construction methods face issues of sparse and noisy connections, destroying ISK performance. To address these issues, we propose DarkFarseer, a novel ISK framework with three key components. First, we propose the Neighbor Hidden Style Enhancement module with a style transfer strategy to enhance the representation of virtual nodes in a temporal-then-spatial manner to better extract the spatial relationships between physical and virtual nodes. Second, we propose Virtual-Component Contrastive Learning, which aims to enrich the node representation by establishing the association between the patterns of virtual nodes and the regional patterns within graph components. Lastly, we design a Similarity-Based Graph Denoising Strategy, which reduces the connectivity strength of noisy connections around virtual nodes and their neighbors based on their temporal information and regional spatial patterns. Extensive experiments demonstrate that DarkFarseer significantly outperforms existing ISK methods.

Figures (4)

• Figure 1: Overall architecture of DarkFarseer.
• Figure 2: Illustrations of Contrastive Scenario (1) and (2).
• Figure 3: Impact of BCC sparsity levels $\mu$, contrastive loss weight $\eta$, and edge-dropping rates $\beta$ on PEMS-BAY.
• Figure 4: Evaluation in various scenarios on PEMS-BAY.