mlsanityData to 7 Oct 2026

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

arXiv 2512.17352 ↗First posted 19 Dec 2025cs.LG cs.AI cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 26 of its 62 references that are in the map. First posted on arXiv 19 Dec 2025.

Builds on

26 of 62 references.

References · 26

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Inductive Representation Learning on Large Graphscited by 6,284
  3. 2019Advances and Open Problems in Federated Learningcited by 3,021
  4. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  5. 2015Gated Graph Sequence Neural Networkscited by 792
  6. 2019GMAN: A Graph Multi-Attention Network for Traffic Predictioncited by 433
  7. 2021Graph Neural Network for Traffic Forecasting: A Surveycited by 260
  8. 2020Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecastingcited by 212
  9. 2018Online Learning: A Comprehensive Surveycited by 203
  10. 2023Spatio-Temporal Graph Neural Networks for Predictive Learning in Urban Computing: A Surveycited by 140
  11. 2020DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphscited by 139
  12. 2020Computing Graph Neural Networks: A Survey from Algorithms to Acceleratorscited by 81
14 more
  1. 2019A Comparative Analysis of XGBoostcited by 80
  2. 2020Reducing Communication in Graph Neural Network Trainingcited by 50
  3. 2021Semi-Decentralized Federated Learning with Cooperative D2D Local Model Aggregationscited by 50
  4. 2019Central Server Free Federated Learning over Single-sided Trust Social Networkscited by 33
  5. 2021Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learningcited by 30
  6. 2023Spatio-Temporal Graph Neural Networks: A Surveycited by 23
  7. 2023Do We Really Need Graph Neural Networks for Traffic Forecasting?cited by 20
  8. 2022Towards Sparsification of Graph Neural Networkscited by 18
  9. 2021SST-GNN: Simplified Spatio-temporal Traffic forecasting model using Graph Neural Networkcited by 9
  10. 2023Semi-decentralized Inference in Heterogeneous Graph Neural Networks for Traffic Demand Forecasting: An Edge-Computing Approachcited by 5
  11. 2024A Survey of Offline and Online Learning-Based Algorithms for Multirotor UAVscited by 2
  12. 2024CDFGNN: a Systematic Design of Cache-based Distributed Full-Batch Graph Neural Network Training with Communication Reductioncited by 2
  13. 2024Graph Pruning Based Spatial and Temporal Graph Convolutional Network with Transfer Learning for Traffic Predictioncited by 1
  14. 2024Semi-decentralized Training of Spatio-Temporal Graph Neural Networks for Traffic Predictioncited by 1

Built on by

Not cited yet.