Traffic flow prediction is a challenging task while most existing works are faced with two main problems in extracting complicated intrinsic and extrinsic features. In terms of intrinsic features, current methods don’t fully exploit different functions of short-term neighboring and long-term periodic temporal patterns. As for extrinsic features, recent works mainly employ hand-crafted fusion strategies to integrate external factors but remain generalization issues. To solve these problems, we propose a meta-learning based multi-source spatio-temporal network (Meta-MSNet). The Meta-MSNet is designed with an encoder-decoder structure. The encoder captures neighboring temporal dependencies while the decoder extracts periodic features. Furthermore, two meta-learning based fusion modules are designed to integrate multi-source external data both on temporal and spatial dimensions. Experiments on three real-world traffic datasets have verified the superiority of the proposed model.

中文翻译：

---

Meta-MSNet：基于元学习的交通流预测多源数据融合

交通流预测是一项具有挑战性的任务，而大多数现有工作在提取复杂的内在和外在特征方面都面临两个主要问题。就内在特征而言，当前的方法没有充分利用短期相邻和长期周期性时间模式的不同功能。至于外在特征，最近的工作主要采用手工融合策略来整合外部因素，但仍然存在泛化问题。为了解决这些问题，我们提出了一种基于元学习的多源时空网络（Meta-MSNet）。Meta-MSNet 采用编码器-解码器结构设计。编码器捕获相邻的时间依赖性，而解码器提取周期性特征。此外，两个基于元学习的融合模块旨在整合时间和空间维度上的多源外部数据。在三个真实世界的交通数据集上的实验验证了所提出模型的优越性。