HiMoE: Heterogeneity-Informed Mixture-of-Experts for Fair Spatial-Temporal Forecasting

Achieving fair prediction performance across nodes is crucial in the spatial-temporal domain, as it ensures the validity and reliability of forecasting outcomes. However, existing models focus primarily on improving the overall accuracy of the prediction, often neglecting the goal of achieving uniformity in the predictions. This task becomes particularly challenging due to the inherent spatial-temporal heterogeneity of the nodes. To address this issue, we propose a novel Heterogeneity-informed Mixture-of-Experts (HiMoE) for fair spatial-temporal forecasting. In particular, we design the Heterogeneity-Informed Graph Convolutional Network (HiGCN), which leverages the fusion of multi-graph and edge masking to flexibly model spatial dependencies. Moreover, we introduce the Node-wise Mixture-of-Experts (NMoE), which allocates prediction tasks of different nodes to suitable experts through graph decoupling routing. To further improve the model, fairness-aware loss and evaluation functions are proposed, optimizing the model with fairness and accuracy as objectives. Experiments on four datasets from different real-world scenarios demonstrate that HiMoE achieves the state-of-the-art performance, outperforming the best baseline with at lease 9.22% in all metrics.