MoGERNN: An Inductive Traffic Predictor for Unobserved Locations in Dynamic Sensing Networks

2025-01-21

AI Summary

To address the challenge of accurately predicting traffic conditions on uncovered road segments in dynamic sensor networks—where sparse and relocatable sensor deployments lead to incomplete spatial coverage—this paper proposes the first end-to-end inductive spatiotemporal graph forecasting framework tailored for unobserved locations. The core innovation is the Mixture-of-Graph-Experts (MoGE) module, which integrates a sparse gating mechanism with multi-graph message aggregators to efficiently model complex spatiotemporal dependencies while enabling zero-shot adaptation to changing sensor configurations without retraining. By synergistically combining graph neural networks, GRUs, Mixture-of-Experts principles, and sparse soft routing, the framework supports fine-tuning-free cross-configuration inference. Extensive experiments on two real-world datasets demonstrate significant improvements over state-of-the-art baselines in forecasting congestion evolution on both observed and unobserved segments. Moreover, the framework exhibits strong robustness under dynamic sensor count variations, and ablation studies validate the efficacy of each component.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Machine Learning: Mixture of Experts (MoE)
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

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
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Given a partially observed road network, how can we predict the traffic state of unobserved locations? While deep learning approaches show exceptional performance in traffic prediction, most assume sensors at all locations of interest, which is impractical due to financial constraints. Furthermore, these methods typically require costly retraining when sensor configurations change. We propose MoGERNN, an inductive spatio-temporal graph representation model, to address these challenges. Inspired by the Mixture of Experts approach in Large Language Models, we introduce a Mixture of Graph Expert (MoGE) block to model complex spatial dependencies through multiple graph message aggregators and a sparse gating network. This block estimates initial states for unobserved locations, which are then processed by a GRU-based Encoder-Decoder that integrates a graph message aggregator to capture spatio-temporal dependencies and predict future states. Experiments on two real-world datasets show MoGERNN consistently outperforms baseline methods for both observed and unobserved locations. MoGERNN can accurately predict congestion evolution even in areas without sensors, offering valuable information for traffic management. Moreover, MoGERNN is adaptable to dynamic sensing networks, maintaining competitive performance even compared to its retrained counterpart. Tests with different numbers of available sensors confirm its consistent superiority, and ablation studies validate the effectiveness of its key modules.

Problem

• Dynamic Sensory Networks
• Traffic Condition Prediction
• Cost-effective Sensor Deployment

Innovation

• MoGERNN
• Sensorless Traffic Prediction
• GRU-based Spatiotemporal Modeling