Adaptive Sparsified Graph Learning Framework for Vessel Behavior Anomalies

2025-02-20

AI Summary

Traditional maritime anomaly detection methods rely on predefined graph structures with spatially fixed nodes, limiting adaptability to dynamic maritime environments. To address this, we propose an adaptive sparse graph modeling framework where timestamps serve as graph nodes—introducing the novel concept of “timestamp nodeification” to explicitly encode spatiotemporal interactions among vessels. We design a multi-vessel dynamic graph construction mechanism that overcomes the constraints of static spatial node representations. Furthermore, we integrate Graph Convolutional Networks (GCNs), Variational Graph Autoencoders (VGAEs), and adaptive sparsification learning to achieve efficient temporal graph representation learning. Evaluated on real-world AIS data, our method achieves a 12.6% improvement in F1-score, attains 87% graph sparsity, and maintains strong spatiotemporal robustness—enabling effective collaborative anomaly detection across multiple vessels.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Reasoning under Uncertainty: Graphical Models

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic 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 query analysis, representation and understanding

Abstract

Graph neural networks have emerged as a powerful tool for learning spatiotemporal interactions. However, conventional approaches often rely on predefined graphs, which may obscure the precise relationships being modeled. Additionally, existing methods typically define nodes based on fixed spatial locations, a strategy that is ill-suited for dynamic environments like maritime environments. Our method introduces an innovative graph representation where timestamps are modeled as distinct nodes, allowing temporal dependencies to be explicitly captured through graph edges. This setup is extended to construct a multi-ship graph that effectively captures spatial interactions while preserving graph sparsity. The graph is processed using Graph Convolutional Network layers to capture spatiotemporal patterns, with a forecasting layer for feature prediction and a Variational Graph Autoencoder for reconstruction, enabling robust anomaly detection.

Problem

• Detects vessel behavior anomalies using adaptive graph learning.
• Captures spatiotemporal interactions with dynamic graph representation.
• Enhances anomaly detection with Variational Graph Autoencoder.

Innovation

• Adaptive sparsified graph learning
• Timestamp-based node modeling
• Variational Graph Autoencoder for anomaly detection