Adaptive Graph Pruning with Sudden-Events Evaluation for Traffic Prediction using Online Semi-Decentralized ST-GNNs

TL;DR

This paper introduces an adaptive graph pruning method for traffic prediction with ST-GNNs that reduces communication overhead at the edge while maintaining accuracy, and proposes a new metric SEPA to evaluate responsiveness to traffic events.

Contribution

It presents a novel adaptive pruning algorithm for ST-GNNs in semi-decentralized traffic prediction and introduces the SEPA metric for better responsiveness evaluation.

Findings

Adaptive pruning maintains accuracy while reducing communication costs.

SEPA metric reveals the importance of spatial connectivity in dynamic traffic prediction.

The approach performs well across multiple datasets and prediction horizons.

Abstract

Spatio-Temporal Graph Neural Networks (ST-GNNs) are well-suited for processing high-frequency data streams from geographically distributed sensors in smart mobility systems. However, their deployment at the edge across distributed compute nodes (cloudlets) createssubstantial communication overhead due to repeated transmission of overlapping node features between neighbouring cloudlets. To address this, we propose an adaptive pruning algorithm that dynamically filters redundant neighbour features while preserving the most informative spatial context for prediction. The algorithm adjusts pruning rates based on recent model performance, allowing each cloudlet to focus on regions experiencing traffic changes without compromising accuracy. Additionally, we introduce the Sudden Event Prediction Accuracy (SEPA), a novel event-focused metric designed to measure responsiveness to traffic slowdowns and recoveries, which are often missed by standard error metrics. We evaluate our approach in an online semi-decentralized setting with traditional FL, server-free FL, and Gossip Learning on two large-scale traffic datasets, PeMS-BAY and PeMSD7-M, across short-, mid-, and long-term prediction horizons. Experiments show that, in contrast to standard metrics, SEPA exposes the true value of spatial connectivity in predicting dynamic and irregular traffic. Our adaptive pruning algorithm maintains prediction accuracy while significantly lowering communication cost in all online semi-decentralized settings, demonstrating that communication can be reduced without compromising responsiveness to critical traffic events.