让每个交通节点选专属专家，提升预测精度
Graph-Conditioned Mixture of Graph Neural Network Experts for Traffic Forecasting
- 按道路拓扑和实时流量，动态分配节点专用专家
- 仅用1.7万参数，比基线降低12%的平均绝对误差
- 适合需要轻量化高精度交通预测的场景
传统时空预测多采用统一骨干网络处理所有节点，但道路区域动态差异显著。本文提出图条件混合专家框架GC-MoE，根据图结构与近期交通输入，为每个节点动态组合一组冻结的预训练时空图神经网络专家。该方法仅训练一个轻量级路由模块（约1.7万参数），在保留150万冻结专家权重的基础上，实现对四个标准基准（PEMS04、PEMS07、METR-LA、PEMS-BAY）的显著改进。相比零参数集成基线，其平均绝对误差（MAE）降低12%，同时保持竞争性均方根误差（RMSE）与平均绝对百分比误差（MAPE）。可选的图条件输出优化层及节点自适应ST-LoRA适配器仅用于消融实验。代码已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。