Graph-Conditioned Mixture of Graph Neural Network Experts for Traffic Forecasting
This work provides an incremental improvement for traffic forecasting by specializing models for different road segments, which is beneficial for urban planning and traffic management.
The paper addresses spatio-temporal forecasting on sensor graphs by proposing GC-MoE, a graph-conditioned mixture of experts framework. It assigns each node a personalized combination of frozen forecasting experts based on graph topology and recent traffic input, improving MAE over a zero-parameter ensemble baseline across four benchmarks while training only ~17K parameters.
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.