Graph-Conditioned Mixture of Graph Neural Network Experts for Traffic Forecasting

• URL: http://arxiv.org/abs/2605.30486v1
• Date: Thu, 28 May 2026 19:05:18 GMT
• Title: Graph-Conditioned Mixture of Graph Neural Network Experts for Traffic Forecasting
• Abstract summary: GC-MoE is a graph-conditioned mixture of experts framework that assigns each node a personalized combination of frozen forecasting experts.<n> GC-MoE combines frozen pretrained-temporal GNN experts with an input-aware, spatially contextualized router.
• Score: 0.1354560757162539
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spatio-temporal forecasting on sensor graphs is commonly tackled with a single backbone architecture applied uniformly across all nodes, although graph regions can exhibit different dynamics. Road segments differ in functional class, structure, and traffic behavior, suggesting that node-wise expert specialization can be useful. We propose GC-MoE, a graph-conditioned mixture of experts framework that assigns each node a personalized combination of frozen forecasting experts based on graph topology and the recent traffic input window. GC-MoE combines frozen pretrained spatio-temporal GNN experts with an input-aware, spatially contextualized router while training only a lightweight routing module. We also study a bounded graph-conditioned output refinement layer as an optional extension and include node-adaptive ST-LoRA adapters only as an ablation diagnostic. Across four standard benchmarks (PEMS04, PEMS07, METR-LA, and PEMS-BAY), GC-MoE improves MAE over a zero-parameter ensemble baseline, with competitive RMSE and MAPE, while training only ~17K parameters on top of 1.5M frozen expert weights. The implementation is available at https://github.com/Ahghaffari/gc_moe.

Related papers

• Dynamic Graph with Similarity-Aware Attention Graph Neural Network for Recommender Systems [0.0]
  This paper proposes a Dynamic Graph SimilarityAware Attention Graph Neural Network framework.<n>It integrates dynamic user similarity graph construction with multi-similarity propagation and attention-based aggregation.<n>Experiments on the MovieLens100K benchmark demonstrate that DG-SA-GNN achieves a Recall@20 of 0.162 and NDCG@20 of 0.065 which is better than the LightGCN baseline in recall.
  arXiv  Detail & Related papers  (2026-05-02T16:33:39Z)
• Semi-supervised Instruction Tuning for Large Language Models on Text-Attributed Graphs [62.544129365882014]
  We propose a novel Semi-supervised Instruction Tuning pipeline for Graph Learning, named SIT-Graph.<n> SIT-Graph is model-agnostic and can be seamlessly integrated into any graph instruction tuning method that utilizes LLMs as the predictor.<n>Extensive experiments demonstrate that when incorporated into state-of-the-art graph instruction tuning methods, SIT-Graph significantly enhances their performance on text-attributed graph benchmarks.
  arXiv  Detail & Related papers  (2026-01-19T08:10:53Z)
• Self-Adaptive Graph Mixture of Models [4.3009319001455975]
  Self-Adaptive Graph Mixture of Models (SAGMM) is a modular and practical framework that learns to automatically select and combine the most appropriate GNN models.<n>We evaluate SAGMM on 16 benchmark datasets covering node classification, graph classification, regression, and link prediction tasks.
  arXiv  Detail & Related papers  (2025-11-17T07:11:06Z)
• DA-MoE: Addressing Depth-Sensitivity in Graph-Level Analysis through Mixture of Experts [70.21017141742763]
  Graph neural networks (GNNs) are gaining popularity for processing graph-structured data. Existing methods generally use a fixed number of GNN layers to generate representations for all graphs. We propose the depth adaptive mixture of expert (DA-MoE) method, which incorporates two main improvements to GNN.
  arXiv  Detail & Related papers  (2024-11-05T11:46:27Z)
• Graph Sparsification via Mixture of Graphs [67.40204130771967]
  We introduce Mixture-of-Graphs (MoG) to dynamically select tailored pruning solutions for each node. MoG incorporates multiple sparsifier experts, each characterized by unique sparsity levels and pruning criteria, and selects the appropriate experts for each node. Experiments on four large-scale OGB datasets and two superpixel datasets, equipped with five GNNs, demonstrate that MoG identifies subgraphs at higher sparsity levels.
  arXiv  Detail & Related papers  (2024-05-23T07:40:21Z)
• Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling [60.0185734837814]
  Graph neural networks (GNNs) have found extensive applications in learning from graph data. To bolster the generalization capacity of GNNs, it has become customary to augment training graph structures with techniques like graph augmentations. This study introduces the concept of Mixture-of-Experts (MoE) to GNNs, with the aim of augmenting their capacity to adapt to a diverse range of training graph structures.
  arXiv  Detail & Related papers  (2023-04-06T01:09:36Z)
• Neural Graph Matching for Pre-training Graph Neural Networks [72.32801428070749]
  Graph neural networks (GNNs) have been shown powerful capacity at modeling structural data. We present a novel Graph Matching based GNN Pre-Training framework, called GMPT. The proposed method can be applied to fully self-supervised pre-training and coarse-grained supervised pre-training.
  arXiv  Detail & Related papers  (2022-03-03T09:53:53Z)
• Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction [123.20238648121445]
  We propose a new self-supervised learning framework, Graph Information Aided Node feature exTraction (GIANT) GIANT makes use of the eXtreme Multi-label Classification (XMC) formalism, which is crucial for fine-tuning the language model based on graph information. We demonstrate the superior performance of GIANT over the standard GNN pipeline on Open Graph Benchmark datasets.
  arXiv  Detail & Related papers  (2021-10-29T19:55:12Z)
• Graph Networks with Spectral Message Passing [1.0742675209112622]
  We introduce the Spectral Graph Network, which applies message passing to both the spatial and spectral domains. Our results show that the Spectral GN promotes efficient training, reaching high performance with fewer training iterations despite having more parameters.
  arXiv  Detail & Related papers  (2020-12-31T21:33:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.