FaST实现千节点大规模时空图一周预测，效率与精度双突破。
FaST: Efficient and Effective Long-Horizon Forecasting for Large-Scale Spatial-Temporal Graphs via Mixture-of-Experts
- 用自适应图代理注意力降低大图计算开销
- 基于门控线性单元的并行专家模块提升扩展性
- 支持672步（15分钟粒度）长时预测，适合大规模城市交通建模
大规模时空图（STG）预测受到广泛关注。现有模型多聚焦短期预测，在扩展至长时程和大图时面临严重计算成本与内存消耗问题。针对此，我们提出FaST框架，基于异质性感知的混合专家（MoE）结构，实现千节点规模下长达一周（672步，15分钟粒度）的高效准确预测。核心创新包括：一、提出自适应图代理注意力机制，缓解传统图卷积与自注意力在大图上的计算负担；二、设计新型并行MoE模块，以门控线性单元（GLUs）替代传统前馈网络，构建高效可扩展的并行结构。在真实数据集上的大量实验表明，FaST不仅在长时预测上达到更优精度，同时显著优于当前最优基线的计算效率。代码已开源：https://github.com/yijizhao/FaST。
原文摘要 · Abstract (English)
Spatial-Temporal Graph (STG) forecasting on large-scale networks has garnered significant attention. However, existing models predominantly focus on short-horizon predictions and suffer from notorious computational costs and memory consumption when scaling to long-horizon predictions and large graphs. Targeting the above challenges, we present FaST, an effective and efficient framework based on heterogeneity-aware Mixture-of-Experts (MoEs) for long-horizon and large-scale STG forecasting, which unlocks one-week-ahead (672 steps at a 15-minute granularity) prediction with thousands of nodes. FaST is underpinned by two key innovations. First, an adaptive graph agent attention mechanism is proposed to alleviate the computational burden inherent in conventional graph convolution and self-attention modules when applied to large-scale graphs. Second, we propose a new parallel MoE module that replaces traditional feed-forward networks with Gated Linear Units (GLUs), enabling an efficient and scalable parallel structure. Extensive experiments on real-world datasets demonstrate that FaST not only delivers superior long-horizon predictive accuracy but also achieves remarkable computational efficiency compared to state-of-the-art baselines. Our source code is available at: https://github.com/yijizhao/FaST.
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。