Spatio-Temporal Graphs Beyond Grids: Benchmark for Maritime Anomaly Detection

2025-12-23

AI Summary

Spatial anchor absence, sparse/irregular trajectories, and multi-granularity anomalies in ungridded maritime traffic scenarios impede robust spatiotemporal graph construction and anomaly detection. Method: We propose the first benchmark for spatiotemporal graph anomaly detection tailored to open, dynamic maritime domains. Specifically: (i) we design an Optimal Matching-based Temporal Alignment and Graph Construction (OMTAD) framework; (ii) we introduce an LLM-driven trajectory synthesizer and anomaly injector to generate semantically plausible, context-consistent anomalies at node-, edge-, and graph-level granularity; and (iii) we establish a fine-grained, GNN-compatible annotation schema. Contribution/Results: We release the first open-source, reproducible benchmark for ungridded spatiotemporal graph anomaly detection—filling a critical gap in systematic evaluation—and thereby advance both methodology development and empirical assessment of ST-GNNs in open, dynamic environments.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Graph-based Machine Learning
• Data Mining & Knowledge Management: Anomaly/Outlier Detection

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs 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 evaluation methodologies and metrics

Abstract

Spatio-temporal graph neural networks (ST-GNNs) have achieved notable success in structured domains such as road traffic and public transportation, where spatial entities can be naturally represented as fixed nodes. In contrast, many real-world systems including maritime traffic lack such fixed anchors, making the construction of spatio-temporal graphs a fundamental challenge. Anomaly detection in these non-grid environments is particularly difficult due to the absence of canonical reference points, the sparsity and irregularity of trajectories, and the fact that anomalies may manifest at multiple granularities. In this work, we introduce a novel benchmark dataset for anomaly detection in the maritime domain, extending the Open Maritime Traffic Analysis Dataset (OMTAD) into a benchmark tailored for graph-based anomaly detection. Our dataset enables systematic evaluation across three different granularities: node-level, edge-level, and graph-level anomalies. We plan to employ two specialized LLM-based agents: emph{Trajectory Synthesizer} and emph{Anomaly Injector} to construct richer interaction contexts and generate semantically meaningful anomalies. We expect this benchmark to promote reproducibility and to foster methodological advances in anomaly detection for non-grid spatio-temporal systems.

Problem

• Detect anomalies in maritime traffic lacking fixed spatial nodes
• Address sparsity and irregularity of trajectories in non-grid environments
• Enable multi-granular anomaly detection at node, edge, and graph levels

Innovation

• LLM-based agents for trajectory synthesis and anomaly injection
• Multi-granularity benchmark for node, edge, and graph anomalies
• Dataset extension enabling systematic evaluation in non-grid systems